Stop the war!
Остановите войну!
for scientists:
default search action
BibTeX records: Jan Peters 0001
@article{DBLP:journals/pami/AbdulsamadNKP24, author = {Hany Abdulsamad and Peter Nickl and Pascal Klink and Jan Peters}, title = {Variational Hierarchical Mixtures for Probabilistic Learning of Inverse Dynamics}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {46}, number = {4}, pages = {1950--1963}, year = {2024}, url = {https://doi.org/10.1109/TPAMI.2023.3314670}, doi = {10.1109/TPAMI.2023.3314670}, timestamp = {Mon, 01 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/AbdulsamadNKP24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/KickiLTBWSP24, author = {Piotr Kicki and Puze Liu and Davide Tateo and Haitham Bou{-}Ammar and Krzysztof Walas and Piotr Skrzypczynski and Jan Peters}, title = {Fast Kinodynamic Planning on the Constraint Manifold With Deep Neural Networks}, journal = {{IEEE} Trans. Robotics}, volume = {40}, pages = {277--297}, year = {2024}, url = {https://doi.org/10.1109/TRO.2023.3326922}, doi = {10.1109/TRO.2023.3326922}, timestamp = {Fri, 08 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/trob/KickiLTBWSP24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/DerstroffCB0024, author = {Cedric Derstroff and Mattia Cerrato and Jannis Brugger and Jan Peters and Stefan Kramer}, editor = {Michael J. Wooldridge and Jennifer G. Dy and Sriraam Natarajan}, title = {Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations}, booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI} 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver, Canada}, pages = {11766--11774}, publisher = {{AAAI} Press}, year = {2024}, url = {https://doi.org/10.1609/aaai.v38i10.29061}, doi = {10.1609/AAAI.V38I10.29061}, timestamp = {Tue, 02 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/DerstroffCB0024.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/VincentMB0RD24, author = {Th{\'{e}}o Vincent and Alberto Maria Metelli and Boris Belousov and Jan Peters and Marcello Restelli and Carlo D'Eramo}, editor = {Michael J. Wooldridge and Jennifer G. Dy and Sriraam Natarajan}, title = {Parameterized Projected Bellman Operator}, booktitle = {Thirty-Eighth {AAAI} Conference on Artificial Intelligence, {AAAI} 2024, Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence, {IAAI} 2024, Fourteenth Symposium on Educational Advances in Artificial Intelligence, {EAAI} 2014, February 20-27, 2024, Vancouver, Canada}, pages = {15402--15410}, publisher = {{AAAI} Press}, year = {2024}, url = {https://doi.org/10.1609/aaai.v38i14.29465}, doi = {10.1609/AAAI.V38I14.29465}, timestamp = {Tue, 02 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/VincentMB0RD24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hri/GoksuCPKK0C24, author = {Yasemin G{\"{o}}ksu and Antonio De Almeida Correia and Vignesh Prasad and Alap Kshirsagar and Dorothea Koert and Jan Peters and Georgia Chalvatzaki}, editor = {Dan Grollman and Elizabeth Broadbent and Wendy Ju and Harold Soh and Tom Williams}, title = {Kinematically Constrained Human-like Bimanual Robot-to-Human Handovers}, booktitle = {Companion of the 2024 {ACM/IEEE} International Conference on Human-Robot Interaction, {HRI} 2024, Boulder, CO, USA, March 11-15, 2024}, pages = {497--501}, publisher = {{ACM}}, year = {2024}, url = {https://doi.org/10.1145/3610978.3640670}, doi = {10.1145/3610978.3640670}, timestamp = {Mon, 01 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hri/GoksuCPKK0C24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hri/HahnePKKS0C24, author = {Fabian Hahne and Vignesh Prasad and Alap Kshirsagar and Dorothea Koert and Ruth Maria Stock{-}Homburg and Jan Peters and Georgia Chalvatzaki}, editor = {Dan Grollman and Elizabeth Broadbent and Wendy Ju and Harold Soh and Tom Williams}, title = {Transition State Clustering for Interaction Segmentation and Learning}, booktitle = {Companion of the 2024 {ACM/IEEE} International Conference on Human-Robot Interaction, {HRI} 2024, Boulder, CO, USA, March 11-15, 2024}, pages = {512--516}, publisher = {{ACM}}, year = {2024}, url = {https://doi.org/10.1145/3610978.3640738}, doi = {10.1145/3610978.3640738}, timestamp = {Mon, 01 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hri/HahnePKKS0C24.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2401-09561, author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters}, title = {Sharing Knowledge in Multi-Task Deep Reinforcement Learning}, journal = {CoRR}, volume = {abs/2401.09561}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2401.09561}, doi = {10.48550/ARXIV.2401.09561}, eprinttype = {arXiv}, eprint = {2401.09561}, timestamp = {Fri, 02 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2401-09561.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-01975, author = {Duy M. H. Nguyen and Nina Lukashina and Tai Nguyen and An T. Le and TrungTin Nguyen and Nhat Ho and Jan Peters and Daniel Sonntag and Viktor Zaverkin and Mathias Niepert}, title = {Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks}, journal = {CoRR}, volume = {abs/2402.01975}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.01975}, doi = {10.48550/ARXIV.2402.01975}, eprinttype = {arXiv}, eprint = {2402.01975}, timestamp = {Fri, 08 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-01975.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-14525, author = {Yasemin G{\"{o}}ksu and Antonio De Almeida Correia and Vignesh Prasad and Alap Kshirsagar and Dorothea Koert and Jan Peters and Georgia Chalvatzaki}, title = {Kinematically Constrained Human-like Bimanual Robot-to-Human Handovers}, journal = {CoRR}, volume = {abs/2402.14525}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.14525}, doi = {10.48550/ARXIV.2402.14525}, eprinttype = {arXiv}, eprint = {2402.14525}, timestamp = {Fri, 22 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-14525.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-14548, author = {Fabian Hahne and Vignesh Prasad and Alap Kshirsagar and Dorothea Koert and Ruth Maria Stock{-}Homburg and Jan Peters and Georgia Chalvatzaki}, title = {Transition State Clustering for Interaction Segmentation and Learning}, journal = {CoRR}, volume = {abs/2402.14548}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.14548}, doi = {10.48550/ARXIV.2402.14548}, eprinttype = {arXiv}, eprint = {2402.14548}, timestamp = {Fri, 22 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-14548.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2402-15347, author = {Alessandro G. Bottero and Carlos E. Luis and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, title = {Information-Theoretic Safe Bayesian Optimization}, journal = {CoRR}, volume = {abs/2402.15347}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2402.15347}, doi = {10.48550/ARXIV.2402.15347}, eprinttype = {arXiv}, eprint = {2402.15347}, timestamp = {Fri, 22 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2402-15347.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2403-02107, author = {Th{\'{e}}o Vincent and Daniel Palenicek and Boris Belousov and Jan Peters and Carlo D'Eramo}, title = {Iterated Q-Network: Beyond the One-Step Bellman Operator}, journal = {CoRR}, volume = {abs/2403.02107}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.02107}, doi = {10.48550/ARXIV.2403.02107}, eprinttype = {arXiv}, eprint = {2403.02107}, timestamp = {Tue, 02 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-02107.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2403-13701, author = {Alina B{\"{o}}hm and Tim Schneider and Boris Belousov and Alap Kshirsagar and Lisa Pui Yee Lin and Katja Doerschner and Knut Drewing and Constantin A. Rothkopf and Jan Peters}, title = {What Matters for Active Texture Recognition With Vision-Based Tactile Sensors}, journal = {CoRR}, volume = {abs/2403.13701}, year = {2024}, url = {https://doi.org/10.48550/arXiv.2403.13701}, doi = {10.48550/ARXIV.2403.13701}, eprinttype = {arXiv}, eprint = {2403.13701}, timestamp = {Mon, 08 Apr 2024 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2403-13701.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/GuKDCPK23, author = {Shangding Gu and Alap Kshirsagar and Yali Du and Guang Chen and Jan Peters and Alois Knoll}, title = {A human-centered safe robot reinforcement learning framework with interactive behaviors}, journal = {Frontiers Neurorobotics}, volume = {17}, year = {2023}, url = {https://doi.org/10.3389/fnbot.2023.1280341}, doi = {10.3389/FNBOT.2023.1280341}, timestamp = {Mon, 01 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/finr/GuKDCPK23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/LutterP23, author = {Michael Lutter and Jan Peters}, title = {Combining physics and deep learning to learn continuous-time dynamics models}, journal = {Int. J. Robotics Res.}, volume = {42}, number = {3}, pages = {83--107}, year = {2023}, url = {https://doi.org/10.1177/02783649231169492}, doi = {10.1177/02783649231169492}, timestamp = {Fri, 07 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/LutterP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/UrainLLDP23, author = {Julen Urain and Anqi Li and Puze Liu and Carlo D'Eramo and Jan Peters}, title = {Composable energy policies for reactive motion generation and reinforcement learning}, journal = {Int. J. Robotics Res.}, volume = {42}, number = {10}, pages = {827--858}, year = {2023}, url = {https://doi.org/10.1177/02783649231179499}, doi = {10.1177/02783649231179499}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijrr/UrainLLDP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/LookKRP23, author = {Andreas Look and Melih Kandemir and Barbara Rakitsch and Jan Peters}, title = {A Deterministic Approximation to Neural SDEs}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {45}, number = {4}, pages = {4023--4037}, year = {2023}, url = {https://doi.org/10.1109/TPAMI.2022.3202237}, doi = {10.1109/TPAMI.2022.3202237}, timestamp = {Tue, 28 Mar 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/LookKRP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/LutterBMFGP23, author = {Michael Lutter and Boris Belousov and Shie Mannor and Dieter Fox and Animesh Garg and Jan Peters}, title = {Continuous-Time Fitted Value Iteration for Robust Policies}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {45}, number = {5}, pages = {5534--5548}, year = {2023}, url = {https://doi.org/10.1109/TPAMI.2022.3215769}, doi = {10.1109/TPAMI.2022.3215769}, timestamp = {Sat, 29 Apr 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/LutterBMFGP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/FlynnRKP23, author = {Hamish Flynn and David Reeb and Melih Kandemir and Jan Peters}, title = {PAC-Bayes Bounds for Bandit Problems: {A} Survey and Experimental Comparison}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {45}, number = {12}, pages = {15308--15327}, year = {2023}, url = {https://doi.org/10.1109/TPAMI.2023.3305381}, doi = {10.1109/TPAMI.2023.3305381}, timestamp = {Tue, 28 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/pami/FlynnRKP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/BjelonicLASTPH23, author = {Filip Bjelonic and Joonho Lee and Philip Arm and Dhionis V. Sako and Davide Tateo and Jan Peters and Marco Hutter}, title = {Learning-Based Design and Control for Quadrupedal Robots With Parallel-Elastic Actuators}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {8}, number = {3}, pages = {1611--1618}, year = {2023}, url = {https://doi.org/10.1109/LRA.2023.3234809}, doi = {10.1109/LRA.2023.3234809}, timestamp = {Sat, 11 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/BjelonicLASTPH23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/JuVAP23, author = {Siwei Ju and Peter van Vliet and Oleg Arenz and Jan Peters}, title = {Digital Twin of a Driver-in-the-Loop Race Car Simulation With Contextual Reinforcement Learning}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {8}, number = {7}, pages = {4107--4114}, year = {2023}, url = {https://doi.org/10.1109/LRA.2023.3279618}, doi = {10.1109/LRA.2023.3279618}, timestamp = {Fri, 07 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/JuVAP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/BuchlerCP23, author = {Dieter B{\"{u}}chler and Roberto Calandra and Jan Peters}, title = {Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots}, journal = {Robotics Auton. Syst.}, volume = {159}, pages = {104230}, year = {2023}, url = {https://doi.org/10.1016/j.robot.2022.104230}, doi = {10.1016/J.ROBOT.2022.104230}, timestamp = {Fri, 06 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/BuchlerCP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tmlr/LookRKP23, author = {Andreas Look and Barbara Rakitsch and Melih Kandemir and Jan Peters}, title = {Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems}, journal = {Trans. Mach. Learn. Res.}, volume = {2023}, year = {2023}, url = {https://openreview.net/forum?id=dqgdBy4Uv5}, timestamp = {Thu, 18 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tmlr/LookRKP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tsmc/LockelJSVP23, author = {Stefan L{\"{o}}ckel and Siwei Ju and Maximilian Schaller and Peter van Vliet and Jan Peters}, title = {An Adaptive Human Driver Model for Realistic Race Car Simulations}, journal = {{IEEE} Trans. Syst. Man Cybern. Syst.}, volume = {53}, number = {11}, pages = {6718--6730}, year = {2023}, url = {https://doi.org/10.1109/TSMC.2023.3285588}, doi = {10.1109/TSMC.2023.3285588}, timestamp = {Thu, 09 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tsmc/LockelJSVP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/LuisBVB023, author = {Carlos E. Luis and Alessandro G. Bottero and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, editor = {Francisco J. R. Ruiz and Jennifer G. Dy and Jan{-}Willem van de Meent}, title = {Model-Based Uncertainty in Value Functions}, booktitle = {International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain}, series = {Proceedings of Machine Learning Research}, volume = {206}, pages = {8029--8052}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v206/luis23a.html}, timestamp = {Mon, 19 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aistats/LuisBVB023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cbs/ZhuNJZAHBHP23, author = {Yaonan Zhu and Shukrullo Nazirjonov and Bingheng Jiang and Jacinto E. Colan Zaita and Tadayoshi Aoyama and Yasuhisa Hasegawa and Boris Belousov and Kay Hansel and Jan Peters}, title = {Visual Tactile Sensor Based Force Estimation for Position-Force Teleoperation}, booktitle = {{IEEE} International Conference on Cyborg and Bionic Systems, {CBS} 2023, Wuhan, China, March 24-26, 2023}, pages = {49--52}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/CBS55922.2023.10115342}, doi = {10.1109/CBS55922.2023.10115342}, timestamp = {Wed, 24 May 2023 09:43:42 +0200}, biburl = {https://dblp.org/rec/conf/cbs/ZhuNJZAHBHP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ecai/RotherW023, author = {David Rother and Thomas H. Weisswange and Jan Peters}, editor = {Kobi Gal and Ann Now{\'{e}} and Grzegorz J. Nalepa and Roy Fairstein and Roxana Radulescu}, title = {Disentangling Interaction Using Maximum Entropy Reinforcement Learning in Multi-Agent Systems}, booktitle = {{ECAI} 2023 - 26th European Conference on Artificial Intelligence, September 30 - October 4, 2023, Krak{\'{o}}w, Poland - Including 12th Conference on Prestigious Applications of Intelligent Systems {(PAIS} 2023)}, series = {Frontiers in Artificial Intelligence and Applications}, volume = {372}, pages = {1994--2001}, publisher = {{IOS} Press}, year = {2023}, url = {https://doi.org/10.3233/FAIA230491}, doi = {10.3233/FAIA230491}, timestamp = {Wed, 18 Oct 2023 09:31:16 +0200}, biburl = {https://dblp.org/rec/conf/ecai/RotherW023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/Zelch0S23, author = {Christoph Zelch and Jan Peters and Oskar von Stryk}, title = {Clustering of Motion Trajectories by a Distance Measure Based on Semantic Features}, booktitle = {22nd {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2023, Austin, TX, USA, December 12-14, 2023}, pages = {1--8}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/Humanoids57100.2023.10375228}, doi = {10.1109/HUMANOIDS57100.2023.10375228}, timestamp = {Tue, 09 Jan 2024 15:27:05 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/Zelch0S23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/Al-HafezTAZ023, author = {Firas Al{-}Hafez and Davide Tateo and Oleg Arenz and Guoping Zhao and Jan Peters}, title = {{LS-IQ:} Implicit Reward Regularization for Inverse Reinforcement Learning}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/pdf?id=o3Q4m8jg4BR}, timestamp = {Fri, 30 Jun 2023 14:38:38 +0200}, biburl = {https://dblp.org/rec/conf/iclr/Al-HafezTAZ023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/PalenicekLC023, author = {Daniel Palenicek and Michael Lutter and Joao Carvalho and Jan Peters}, title = {Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning}, booktitle = {The Eleventh International Conference on Learning Representations, {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023}, publisher = {OpenReview.net}, year = {2023}, url = {https://openreview.net/pdf?id=H4Ncs5jhTCu}, timestamp = {Fri, 30 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/PalenicekLC023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/ZelchPS23, author = {Christoph Zelch and Jan Peters and Oskar von Stryk}, title = {Start State Selection for Control Policy Learning from Optimal Trajectories}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2023, London, UK, May 29 - June 2, 2023}, pages = {3247--3253}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICRA48891.2023.10160978}, doi = {10.1109/ICRA48891.2023.10160978}, timestamp = {Tue, 08 Aug 2023 10:24:29 +0200}, biburl = {https://dblp.org/rec/conf/icra/ZelchPS23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/UrainFPC23, author = {Julen Urain and Niklas Funk and Jan Peters and Georgia Chalvatzaki}, title = {SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2023, London, UK, May 29 - June 2, 2023}, pages = {5923--5930}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICRA48891.2023.10161569}, doi = {10.1109/ICRA48891.2023.10161569}, timestamp = {Tue, 08 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/UrainFPC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LiuZTJHPC23, author = {Puze Liu and Kuo Zhang and Davide Tateo and Snehal Jauhri and Zhiyuan Hu and Jan Peters and Georgia Chalvatzaki}, title = {Safe Reinforcement Learning of Dynamic High-Dimensional Robotic Tasks: Navigation, Manipulation, Interaction}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2023, London, UK, May 29 - June 2, 2023}, pages = {9449--9456}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICRA48891.2023.10161548}, doi = {10.1109/ICRA48891.2023.10161548}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/LiuZTJHPC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/HanselUPC23, author = {Kay Hansel and Julen Urain and Jan Peters and Georgia Chalvatzaki}, title = {Hierarchical Policy Blending as Inference for Reactive Robot Control}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2023, London, UK, May 29 - June 2, 2023}, pages = {10181--10188}, publisher = {{IEEE}}, year = {2023}, url = {https://doi.org/10.1109/ICRA48891.2023.10161374}, doi = {10.1109/ICRA48891.2023.10161374}, timestamp = {Tue, 08 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/HanselUPC23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Carvalho0BK023, author = {Jo{\~{a}}o Carvalho and An T. Le and Mark Baierl and Dorothea Koert and Jan Peters}, title = {Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models}, booktitle = {{IROS}}, pages = {1916--1923}, year = {2023}, url = {https://doi.org/10.1109/IROS55552.2023.10342382}, doi = {10.1109/IROS55552.2023.10342382}, timestamp = {Fri, 05 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/Carvalho0BK023.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LachFHLR0C23, author = {Luca Lach and Niklas Funk and Robert Haschke and S{\'{e}}verin Lemaignan and Helge Joachim Ritter and Jan Peters and Georgia Chalvatzaki}, title = {Placing by Touching: An Empirical Study on the Importance of Tactile Sensing for Precise Object Placing}, booktitle = {{IROS}}, pages = {8964--8971}, year = {2023}, url = {https://doi.org/10.1109/IROS55552.2023.10342340}, doi = {10.1109/IROS55552.2023.10342340}, timestamp = {Fri, 05 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LachFHLR0C23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/l4dc/0001H0C23, author = {An T. Le and Kay Hansel and Jan Peters and Georgia Chalvatzaki}, editor = {Nikolai Matni and Manfred Morari and George J. Pappas}, title = {Hierarchical Policy Blending As Optimal Transport}, booktitle = {Learning for Dynamics and Control Conference, {L4DC} 2023, 15-16 June 2023, Philadelphia, PA, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {211}, pages = {797--812}, publisher = {{PMLR}}, year = {2023}, url = {https://proceedings.mlr.press/v211/le23a.html}, timestamp = {Fri, 16 Jun 2023 14:48:17 +0200}, biburl = {https://dblp.org/rec/conf/l4dc/0001H0C23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/0001CBP23, author = {An T. Le and Georgia Chalvatzaki and Armin Biess and Jan Peters}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, title = {Accelerating Motion Planning via Optimal Transport}, booktitle = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023}, year = {2023}, url = {http://papers.nips.cc/paper\_files/paper/2023/hash/f7a94134f1c726796c6f81fb946e489d-Abstract-Conference.html}, timestamp = {Fri, 08 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/0001CBP23.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-03509, author = {Filip Bjelonic and Joonho Lee and Philip Arm and Dhionis V. Sako and Davide Tateo and Jan Peters and Marco Hutter}, title = {Learning-based Design and Control for Quadrupedal Robots with Parallel-Elastic Actuators}, journal = {CoRR}, volume = {abs/2301.03509}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.03509}, doi = {10.48550/ARXIV.2301.03509}, eprinttype = {arXiv}, eprint = {2301.03509}, timestamp = {Mon, 27 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-03509.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2301-04330, author = {Piotr Kicki and Puze Liu and Davide Tateo and Haitham Bou{-}Ammar and Krzysztof Walas and Piotr Skrzypczynski and Jan Peters}, title = {Fast Kinodynamic Planning on the Constraint Manifold with Deep Neural Networks}, journal = {CoRR}, volume = {abs/2301.04330}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2301.04330}, doi = {10.48550/ARXIV.2301.04330}, eprinttype = {arXiv}, eprint = {2301.04330}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2301-04330.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-12526, author = {Carlos E. Luis and Alessandro G. Bottero and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, title = {Model-Based Uncertainty in Value Functions}, journal = {CoRR}, volume = {abs/2302.12526}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.12526}, doi = {10.48550/ARXIV.2302.12526}, eprinttype = {arXiv}, eprint = {2302.12526}, timestamp = {Tue, 28 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-12526.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2302-13137, author = {Shangding Gu and Alap Kshirsagar and Yali Du and Guang Chen and Yaodong Yang and Jan Peters and Alois C. Knoll}, title = {A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors}, journal = {CoRR}, volume = {abs/2302.13137}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2302.13137}, doi = {10.48550/ARXIV.2302.13137}, eprinttype = {arXiv}, eprint = {2302.13137}, timestamp = {Fri, 12 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2302-13137.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-00599, author = {Firas Al{-}Hafez and Davide Tateo and Oleg Arenz and Guoping Zhao and Jan Peters}, title = {{LS-IQ:} Implicit Reward Regularization for Inverse Reinforcement Learning}, journal = {CoRR}, volume = {abs/2303.00599}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.00599}, doi = {10.48550/ARXIV.2303.00599}, eprinttype = {arXiv}, eprint = {2303.00599}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-00599.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-03955, author = {Daniel Palenicek and Michael Lutter and Joao Carvalho and Jan Peters}, title = {Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning}, journal = {CoRR}, volume = {abs/2303.03955}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.03955}, doi = {10.48550/ARXIV.2303.03955}, eprinttype = {arXiv}, eprint = {2303.03955}, timestamp = {Wed, 15 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-03955.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2303-04725, author = {Johanna Bethge and Maik Pfefferkorn and Alexander Rose and Jan Peters and Rolf Findeisen}, title = {Model Predictive Control with Gaussian-Process-Supported Dynamical Constraints for Autonomous Vehicles}, journal = {CoRR}, volume = {abs/2303.04725}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2303.04725}, doi = {10.48550/ARXIV.2303.04725}, eprinttype = {arXiv}, eprint = {2303.04725}, timestamp = {Thu, 31 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2303-04725.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2305-01773, author = {Andreas Look and Melih Kandemir and Barbara Rakitsch and Jan Peters}, title = {Cheap and Deterministic Inference for Deep State-Space Models of Interacting Dynamical Systems}, journal = {CoRR}, volume = {abs/2305.01773}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2305.01773}, doi = {10.48550/ARXIV.2305.01773}, eprinttype = {arXiv}, eprint = {2305.01773}, timestamp = {Fri, 05 May 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2305-01773.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2307-06055, author = {Jihao Andreas Lin and Joe Watson and Pascal Klink and Jan Peters}, title = {Function-Space Regularization for Deep Bayesian Classification}, journal = {CoRR}, volume = {abs/2307.06055}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2307.06055}, doi = {10.48550/ARXIV.2307.06055}, eprinttype = {arXiv}, eprint = {2307.06055}, timestamp = {Mon, 24 Jul 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2307-06055.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-01557, author = {Jo{\~{a}}o Carvalho and An T. Le and Mark Baierl and Dorothea Koert and Jan Peters}, title = {Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models}, journal = {CoRR}, volume = {abs/2308.01557}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.01557}, doi = {10.48550/ARXIV.2308.01557}, eprinttype = {arXiv}, eprint = {2308.01557}, timestamp = {Tue, 22 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-01557.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2308-06590, author = {Carlos E. Luis and Alessandro G. Bottero and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, title = {Value-Distributional Model-Based Reinforcement Learning}, journal = {CoRR}, volume = {abs/2308.06590}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2308.06590}, doi = {10.48550/ARXIV.2308.06590}, eprinttype = {arXiv}, eprint = {2308.06590}, timestamp = {Wed, 23 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2308-06590.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-08256, author = {Andreas Look and Melih Kandemir and Barbara Rakitsch and Jan Peters}, title = {Sampling-Free Probabilistic Deep State-Space Models}, journal = {CoRR}, volume = {abs/2309.08256}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.08256}, doi = {10.48550/ARXIV.2309.08256}, eprinttype = {arXiv}, eprint = {2309.08256}, timestamp = {Fri, 22 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-08256.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-14091, author = {Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {On the Benefit of Optimal Transport for Curriculum Reinforcement Learning}, journal = {CoRR}, volume = {abs/2309.14091}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.14091}, doi = {10.48550/ARXIV.2309.14091}, eprinttype = {arXiv}, eprint = {2309.14091}, timestamp = {Wed, 27 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-14091.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-14096, author = {Pascal Klink and Florian Wolf and Kai Ploeger and Jan Peters and Joni Pajarinen}, title = {Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning}, journal = {CoRR}, volume = {abs/2309.14096}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.14096}, doi = {10.48550/ARXIV.2309.14096}, eprinttype = {arXiv}, eprint = {2309.14096}, timestamp = {Wed, 27 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-14096.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-14298, author = {Hamish Flynn and David Reeb and Melih Kandemir and Jan Peters}, title = {Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures}, journal = {CoRR}, volume = {abs/2309.14298}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.14298}, doi = {10.48550/ARXIV.2309.14298}, eprinttype = {arXiv}, eprint = {2309.14298}, timestamp = {Tue, 17 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-14298.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2309-15970, author = {An T. Le and Georgia Chalvatzaki and Armin Biess and Jan Peters}, title = {Accelerating Motion Planning via Optimal Transport}, journal = {CoRR}, volume = {abs/2309.15970}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2309.15970}, doi = {10.48550/ARXIV.2309.15970}, eprinttype = {arXiv}, eprint = {2309.15970}, timestamp = {Tue, 17 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2309-15970.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-01642, author = {Aryaman Reddi and Maximilian T{\"{o}}lle and Jan Peters and Georgia Chalvatzaki and Carlo D'Eramo}, title = {Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula}, journal = {CoRR}, volume = {abs/2311.01642}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.01642}, doi = {10.48550/ARXIV.2311.01642}, eprinttype = {arXiv}, eprint = {2311.01642}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-01642.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-01885, author = {Gabriele Tiboni and Pascal Klink and Jan Peters and Tatiana Tommasi and Carlo D'Eramo and Georgia Chalvatzaki}, title = {Domain Randomization via Entropy Maximization}, journal = {CoRR}, volume = {abs/2311.01885}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.01885}, doi = {10.48550/ARXIV.2311.01885}, eprinttype = {arXiv}, eprint = {2311.01885}, timestamp = {Tue, 07 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-01885.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-02496, author = {Firas Al{-}Hafez and Guoping Zhao and Jan Peters and Davide Tateo}, title = {LocoMuJoCo: {A} Comprehensive Imitation Learning Benchmark for Locomotion}, journal = {CoRR}, volume = {abs/2311.02496}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.02496}, doi = {10.48550/ARXIV.2311.02496}, eprinttype = {arXiv}, eprint = {2311.02496}, timestamp = {Wed, 08 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-02496.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-04082, author = {Firas Al{-}Hafez and Guoping Zhao and Jan Peters and Davide Tateo}, title = {Time-Efficient Reinforcement Learning with Stochastic Stateful Policies}, journal = {CoRR}, volume = {abs/2311.04082}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.04082}, doi = {10.48550/ARXIV.2311.04082}, eprinttype = {arXiv}, eprint = {2311.04082}, timestamp = {Tue, 14 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-04082.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-07245, author = {Luca Lach and Robert Haschke and Davide Tateo and Jan Peters and Helge J. Ritter and J{\'{u}}lia Borr{\`{a}}s Sol and Carme Torras}, title = {Towards Transferring Tactile-based Continuous Force Control Policies from Simulation to Robot}, journal = {CoRR}, volume = {abs/2311.07245}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.07245}, doi = {10.48550/ARXIV.2311.07245}, eprinttype = {arXiv}, eprint = {2311.07245}, timestamp = {Wed, 15 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-07245.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-11385, author = {Ahmed Hendawy and Jan Peters and Carlo D'Eramo}, title = {Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts}, journal = {CoRR}, volume = {abs/2311.11385}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.11385}, doi = {10.48550/ARXIV.2311.11385}, eprinttype = {arXiv}, eprint = {2311.11385}, timestamp = {Thu, 23 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-11385.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-16380, author = {Vignesh Prasad and Lea Heitlinger and Dorothea Koert and Ruth Stock{-}Homburg and Jan Peters and Georgia Chalvatzaki}, title = {Learning Multimodal Latent Dynamics for Human-Robot Interaction}, journal = {CoRR}, volume = {abs/2311.16380}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.16380}, doi = {10.48550/ARXIV.2311.16380}, eprinttype = {arXiv}, eprint = {2311.16380}, timestamp = {Mon, 04 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-16380.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2311-16656, author = {Theo Gruner and Boris Belousov and Fabio Muratore and Daniel Palenicek and Jan Peters}, title = {Pseudo-Likelihood Inference}, journal = {CoRR}, volume = {abs/2311.16656}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2311.16656}, doi = {10.48550/ARXIV.2311.16656}, eprinttype = {arXiv}, eprint = {2311.16656}, timestamp = {Mon, 04 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2311-16656.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-01236, author = {Niklas Funk and Erik Helmut and Georgia Chalvatzaki and Roberto Calandra and Jan Peters}, title = {Evetac: An Event-based Optical Tactile Sensor for Robotic Manipulation}, journal = {CoRR}, volume = {abs/2312.01236}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.01236}, doi = {10.48550/ARXIV.2312.01236}, eprinttype = {arXiv}, eprint = {2312.01236}, timestamp = {Fri, 08 Dec 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-01236.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-04386, author = {Carlos E. Luis and Alessandro G. Bottero and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, title = {Model-Based Epistemic Variance of Values for Risk-Aware Policy Optimization}, journal = {CoRR}, volume = {abs/2312.04386}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.04386}, doi = {10.48550/ARXIV.2312.04386}, eprinttype = {arXiv}, eprint = {2312.04386}, timestamp = {Tue, 02 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-04386.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-09950, author = {Cedric Derstroff and Mattia Cerrato and Jannis Brugger and Jan Peters and Stefan Kramer}, title = {Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations}, journal = {CoRR}, volume = {abs/2312.09950}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.09950}, doi = {10.48550/ARXIV.2312.09950}, eprinttype = {arXiv}, eprint = {2312.09950}, timestamp = {Mon, 22 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-09950.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2312-12869, author = {Th{\'{e}}o Vincent and Alberto Maria Metelli and Boris Belousov and Jan Peters and Marcello Restelli and Carlo D'Eramo}, title = {Parameterized Projected Bellman Operator}, journal = {CoRR}, volume = {abs/2312.12869}, year = {2023}, url = {https://doi.org/10.48550/arXiv.2312.12869}, doi = {10.48550/ARXIV.2312.12869}, eprinttype = {arXiv}, eprint = {2312.12869}, timestamp = {Wed, 17 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2312-12869.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/algorithms/ParisiTHDPP22, author = {Simone Parisi and Davide Tateo and Maximilian Hensel and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Long-Term Visitation Value for Deep Exploration in Sparse-Reward Reinforcement Learning}, journal = {Algorithms}, volume = {15}, number = {3}, pages = {81}, year = {2022}, url = {https://doi.org/10.3390/a15030081}, doi = {10.3390/A15030081}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/algorithms/ParisiTHDPP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/datamine/FlynnRKP22, author = {Hamish Flynn and David Reeb and Melih Kandemir and Jan Peters}, title = {PAC-Bayesian lifelong learning for multi-armed bandits}, journal = {Data Min. Knowl. Discov.}, volume = {36}, number = {2}, pages = {841--876}, year = {2022}, url = {https://doi.org/10.1007/s10618-022-00825-4}, doi = {10.1007/S10618-022-00825-4}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/datamine/FlynnRKP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/MuratoreRTYGP22, author = {Fabio Muratore and Fabio Ramos and Greg Turk and Wenhao Yu and Michael Gienger and Jan Peters}, title = {Robot Learning From Randomized Simulations: {A} Review}, journal = {Frontiers Robotics {AI}}, volume = {9}, pages = {799893}, year = {2022}, url = {https://doi.org/10.3389/frobt.2022.799893}, doi = {10.3389/FROBT.2022.799893}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/firai/MuratoreRTYGP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijon/YouACP22, author = {Bang You and Oleg Arenz and Youping Chen and Jan Peters}, title = {Integrating contrastive learning with dynamic models for reinforcement learning from images}, journal = {Neurocomputing}, volume = {476}, pages = {102--114}, year = {2022}, url = {https://doi.org/10.1016/j.neucom.2021.12.094}, doi = {10.1016/J.NEUCOM.2021.12.094}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijon/YouACP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijsr/PrasadSP22, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, title = {Human-Robot Handshaking: {A} Review}, journal = {Int. J. Soc. Robotics}, volume = {14}, number = {1}, pages = {277--293}, year = {2022}, url = {https://doi.org/10.1007/s12369-021-00763-z}, doi = {10.1007/S12369-021-00763-Z}, timestamp = {Wed, 23 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijsr/PrasadSP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jair/Cowen-RiversLTW22, author = {Alexander I. Cowen{-}Rivers and Wenlong Lyu and Rasul Tutunov and Zhi Wang and Antoine Grosnit and Ryan{-}Rhys Griffiths and Alexandre Max Maraval and Jianye Hao and Jun Wang and Jan Peters and Haitham Bou{-}Ammar}, title = {{HEBO:} An Empirical Study of Assumptions in Bayesian Optimisation}, journal = {J. Artif. Intell. Res.}, volume = {74}, pages = {1269--1349}, year = {2022}, url = {https://doi.org/10.1613/jair.1.13643}, doi = {10.1613/JAIR.1.13643}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jair/Cowen-RiversLTW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/make/MoosHASCP22, author = {Janosch Moos and Kay Hansel and Hany Abdulsamad and Svenja Stark and Debora Clever and Jan Peters}, title = {Robust Reinforcement Learning: {A} Review of Foundations and Recent Advances}, journal = {Mach. Learn. Knowl. Extr.}, volume = {4}, number = {1}, pages = {276--315}, year = {2022}, url = {https://doi.org/10.3390/make4010013}, doi = {10.3390/MAKE4010013}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/make/MoosHASCP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/TosattoCP22, author = {Samuele Tosatto and Jo{\~{a}}o Carvalho and Jan Peters}, title = {Batch Reinforcement Learning With a Nonparametric Off-Policy Policy Gradient}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {44}, number = {10}, pages = {5996--6010}, year = {2022}, url = {https://doi.org/10.1109/TPAMI.2021.3088063}, doi = {10.1109/TPAMI.2021.3088063}, timestamp = {Thu, 22 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/TosattoCP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/AkrourTP22, author = {Riad Akrour and Davide Tateo and Jan Peters}, title = {Continuous Action Reinforcement Learning From a Mixture of Interpretable Experts}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {44}, number = {10}, pages = {6795--6806}, year = {2022}, url = {https://doi.org/10.1109/TPAMI.2021.3103132}, doi = {10.1109/TPAMI.2021.3103132}, timestamp = {Thu, 22 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/AkrourTP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/FunkSMYJWGWBSBW22, author = {Niklas Funk and Charles B. Schaff and Rishabh Madan and Takuma Yoneda and Julen Urain De Jesus and Joe Watson and Ethan K. Gordon and Felix Widmaier and Stefan Bauer and Siddhartha S. Srinivasa and Tapomayukh Bhattacharjee and Matthew R. Walter and Jan Peters}, title = {Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {1}, pages = {478--485}, year = {2022}, url = {https://doi.org/10.1109/LRA.2021.3129139}, doi = {10.1109/LRA.2021.3129139}, timestamp = {Wed, 15 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/FunkSMYJWGWBSBW22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/JauhriPC22, author = {Snehal Jauhri and Jan Peters and Georgia Chalvatzaki}, title = {Robot Learning of Mobile Manipulation With Reachability Behavior Priors}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {3}, pages = {8399--8406}, year = {2022}, url = {https://doi.org/10.1109/LRA.2022.3188109}, doi = {10.1109/LRA.2022.3188109}, timestamp = {Mon, 08 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/JauhriPC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/DamCPP22, author = {Tuan Dam and Georgia Chalvatzaki and Jan Peters and Joni Pajarinen}, title = {Monte-Carlo Robot Path Planning}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {4}, pages = {11213--11220}, year = {2022}, url = {https://doi.org/10.1109/LRA.2022.3199674}, doi = {10.1109/LRA.2022.3199674}, timestamp = {Mon, 05 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/DamCPP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/UrainTP22, author = {Julen Urain and Davide Tateo and Jan Peters}, title = {Learning Stable Vector Fields on Lie Groups}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {7}, number = {4}, pages = {12569--12576}, year = {2022}, url = {https://doi.org/10.1109/LRA.2022.3219019}, doi = {10.1109/LRA.2022.3219019}, timestamp = {Mon, 28 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/UrainTP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/ZhengVPS22, author = {Yi Zheng and Filipe Veiga and Jan Peters and Veronica J. Santos}, title = {Autonomous Learning of Page Flipping Movements via Tactile Feedback}, journal = {{IEEE} Trans. Robotics}, volume = {38}, number = {5}, pages = {2734--2749}, year = {2022}, url = {https://doi.org/10.1109/TRO.2022.3168731}, doi = {10.1109/TRO.2022.3168731}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/trob/ZhengVPS22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/BuchlerGCBSP22, author = {Dieter B{\"{u}}chler and Simon Guist and Roberto Calandra and Vincent Berenz and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning to Play Table Tennis From Scratch Using Muscular Robots}, journal = {{IEEE} Trans. Robotics}, volume = {38}, number = {6}, pages = {3850--3860}, year = {2022}, url = {https://doi.org/10.1109/TRO.2022.3176207}, doi = {10.1109/TRO.2022.3176207}, timestamp = {Sun, 15 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/trob/BuchlerGCBSP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/MemmelLT022, author = {Marius Memmel and Puze Liu and Davide Tateo and Jan Peters}, editor = {Gustau Camps{-}Valls and Francisco J. R. Ruiz and Isabel Valera}, title = {Dimensionality Reduction and Prioritized Exploration for Policy Search}, booktitle = {International Conference on Artificial Intelligence and Statistics, {AISTATS} 2022, 28-30 March 2022, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {151}, pages = {2134--2157}, publisher = {{PMLR}}, year = {2022}, url = {https://proceedings.mlr.press/v151/memmel22a.html}, timestamp = {Sat, 30 Sep 2023 09:34:08 +0200}, biburl = {https://dblp.org/rec/conf/aistats/MemmelLT022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/Watson022, author = {Joe Watson and Jan Peters}, editor = {Karen Liu and Dana Kulic and Jeffrey Ichnowski}, title = {Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes}, booktitle = {Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland, New Zealand}, series = {Proceedings of Machine Learning Research}, volume = {205}, pages = {67--79}, publisher = {{PMLR}}, year = {2022}, url = {https://proceedings.mlr.press/v205/watson23a.html}, timestamp = {Wed, 15 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/corl/Watson022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/VorndammeCLKFPH22, author = {Jonathan Vorndamme and Jo{\~{a}}o Carvalho and Riddhiman Laha and Dorothea Koert and Luis F. C. Figueredo and Jan Peters and Sami Haddadin}, title = {Integrated Bi-Manual Motion Generation and Control shaped for Probabilistic Movement Primitives}, booktitle = {21st {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2022, Ginowan, Japan, November 28-30, 2022}, pages = {202--209}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/Humanoids53995.2022.10000149}, doi = {10.1109/HUMANOIDS53995.2022.10000149}, timestamp = {Tue, 09 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/VorndammeCLKFPH22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/CarvalhoKDP22, author = {Jo{\~{a}}o Carvalho and Dorothea Koert and Marek Daniv and Jan Peters}, title = {Adapting Object-Centric Probabilistic Movement Primitives with Residual Reinforcement Learning}, booktitle = {21st {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2022, Ginowan, Japan, November 28-30, 2022}, pages = {405--412}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/Humanoids53995.2022.10000148}, doi = {10.1109/HUMANOIDS53995.2022.10000148}, timestamp = {Tue, 17 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/CarvalhoKDP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/PrasadKSPC22, author = {Vignesh Prasad and Dorothea Koert and Ruth Stock{-}Homburg and Jan Peters and Georgia Chalvatzaki}, title = {{MILD:} Multimodal Interactive Latent Dynamics for Learning Human-Robot Interaction}, booktitle = {21st {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2022, Ginowan, Japan, November 28-30, 2022}, pages = {472--479}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/Humanoids53995.2022.10000239}, doi = {10.1109/HUMANOIDS53995.2022.10000239}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/PrasadKSPC22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/GalljamovZBSP22, author = {Rustam Galljamov and Guoping Zhao and Boris Belousov and Andr{\'{e}} Seyfarth and Jan Peters}, title = {Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking}, booktitle = {21st {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2022, Ginowan, Japan, November 28-30, 2022}, pages = {587--593}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/Humanoids53995.2022.10000068}, doi = {10.1109/HUMANOIDS53995.2022.10000068}, timestamp = {Tue, 17 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/GalljamovZBSP22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/KlinkD0P22, author = {Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Boosted Curriculum Reinforcement Learning}, booktitle = {The Tenth International Conference on Learning Representations, {ICLR} 2022, Virtual Event, April 25-29, 2022}, publisher = {OpenReview.net}, year = {2022}, url = {https://openreview.net/forum?id=anbBFlX1tJ1}, timestamp = {Sat, 20 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iclr/KlinkD0P22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/KlinkYD0P22, author = {Pascal Klink and Haoyi Yang and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, editor = {Kamalika Chaudhuri and Stefanie Jegelka and Le Song and Csaba Szepesv{\'{a}}ri and Gang Niu and Sivan Sabato}, title = {Curriculum Reinforcement Learning via Constrained Optimal Transport}, booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July 2022, Baltimore, Maryland, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {162}, pages = {11341--11358}, publisher = {{PMLR}}, year = {2022}, url = {https://proceedings.mlr.press/v162/klink22a.html}, timestamp = {Tue, 12 Jul 2022 17:36:52 +0200}, biburl = {https://dblp.org/rec/conf/icml/KlinkYD0P22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Ploeger022, author = {Kai Ploeger and Jan Peters}, title = {Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2022, Kyoto, Japan, October 23-27, 2022}, pages = {1139--1144}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IROS47612.2022.9981678}, doi = {10.1109/IROS47612.2022.9981678}, timestamp = {Tue, 03 Jan 2023 14:18:21 +0100}, biburl = {https://dblp.org/rec/conf/iros/Ploeger022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LiuZTJ0C22, author = {Puze Liu and Kuo Zhang and Davide Tateo and Snehal Jauhri and Jan Peters and Georgia Chalvatzaki}, title = {Regularized Deep Signed Distance Fields for Reactive Motion Generation}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2022, Kyoto, Japan, October 23-27, 2022}, pages = {6673--6680}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IROS47612.2022.9981456}, doi = {10.1109/IROS47612.2022.9981456}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LiuZTJ0C22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Urain0LCB022, author = {Julen Urain and An T. Le and Alexander Lambert and Georgia Chalvatzaki and Byron Boots and Jan Peters}, title = {Learning Implicit Priors for Motion Optimization}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2022, Kyoto, Japan, October 23-27, 2022}, pages = {7672--7679}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IROS47612.2022.9981264}, doi = {10.1109/IROS47612.2022.9981264}, timestamp = {Tue, 03 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/Urain0LCB022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/SchneiderBCRJ022, author = {Tim Schneider and Boris Belousov and Georgia Chalvatzaki and Diego Romeres and Devesh K. Jha and Jan Peters}, title = {Active Exploration for Robotic Manipulation}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2022, Kyoto, Japan, October 23-27, 2022}, pages = {9355--9362}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IROS47612.2022.9982061}, doi = {10.1109/IROS47612.2022.9982061}, timestamp = {Tue, 03 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/SchneiderBCRJ022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/FunkMC022, author = {Niklas Funk and Svenja Menzenbach and Georgia Chalvatzaki and Jan Peters}, title = {Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2022, Kyoto, Japan, October 23-27, 2022}, pages = {10215--10222}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/IROS47612.2022.9981784}, doi = {10.1109/IROS47612.2022.9981784}, timestamp = {Tue, 03 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/FunkMC022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BotteroLVB022, author = {Alessandro G. Bottero and Carlos E. Luis and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, title = {Information-Theoretic Safe Exploration with Gaussian Processes}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, year = {2022}, url = {http://papers.nips.cc/paper\_files/paper/2022/hash/c628644624c1be9c8cfb1541fa6421fd-Abstract-Conference.html}, timestamp = {Mon, 08 Jan 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/BotteroLVB022.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/urai/AsmanisMC0M22, author = {Ioannis Asmanis and Panagiotis Mermigkas and Georgia Chalvatzaki and Jan Peters and Petros Maragos}, title = {A Semantic Enhancement of Unified Geometric Representations for Improving Indoor Visual {SLAM}}, booktitle = {19th International Conference on Ubiquitous Robots, {UR} 2022, Jeju, South Korea, July 4-6, 2022}, pages = {288--294}, publisher = {{IEEE}}, year = {2022}, url = {https://doi.org/10.1109/UR55393.2022.9826249}, doi = {10.1109/UR55393.2022.9826249}, timestamp = {Tue, 19 Jul 2022 18:11:02 +0200}, biburl = {https://dblp.org/rec/conf/urai/AsmanisMC0M22.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2201-09612, author = {Tianyu Ren and Alexander Imani Cowen{-}Rivers and Haitham Bou{-}Ammar and Jan Peters}, title = {Learning Geometric Constraints in Task and Motion Planning}, journal = {CoRR}, volume = {abs/2201.09612}, year = {2022}, url = {https://arxiv.org/abs/2201.09612}, eprinttype = {arXiv}, eprint = {2201.09612}, timestamp = {Tue, 01 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2201-09612.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2202-07071, author = {Tuan Dam and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {A Unified Perspective on Value Backup and Exploration in Monte-Carlo Tree Search}, journal = {CoRR}, volume = {abs/2202.07071}, year = {2022}, url = {https://arxiv.org/abs/2202.07071}, eprinttype = {arXiv}, eprint = {2202.07071}, timestamp = {Fri, 18 Feb 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2202-07071.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-01810, author = {Bang You and Oleg Arenz and Youping Chen and Jan Peters}, title = {Integrating Contrastive Learning with Dynamic Models for Reinforcement Learning from Images}, journal = {CoRR}, volume = {abs/2203.01810}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.01810}, doi = {10.48550/ARXIV.2203.01810}, eprinttype = {arXiv}, eprint = {2203.01810}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-01810.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-01909, author = {Stefan L{\"{o}}ckel and Siwei Ju and Maximilian Schaller and Peter van Vliet and Jan Peters}, title = {An Adaptive Human Driver Model for Realistic Race Car Simulations}, journal = {CoRR}, volume = {abs/2203.01909}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.01909}, doi = {10.48550/ARXIV.2203.01909}, eprinttype = {arXiv}, eprint = {2203.01909}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-01909.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-03303, author = {Hamish Flynn and David Reeb and Melih Kandemir and Jan Peters}, title = {PAC-Bayesian Lifelong Learning For Multi-Armed Bandits}, journal = {CoRR}, volume = {abs/2203.03303}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.03303}, doi = {10.48550/ARXIV.2203.03303}, eprinttype = {arXiv}, eprint = {2203.03303}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-03303.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-03917, author = {Jo{\~{a}}o Carvalho and Jan Peters}, title = {An Analysis of Measure-Valued Derivatives for Policy Gradients}, journal = {CoRR}, volume = {abs/2203.03917}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.03917}, doi = {10.48550/ARXIV.2203.03917}, eprinttype = {arXiv}, eprint = {2203.03917}, timestamp = {Tue, 20 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-03917.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-03918, author = {Jo{\~{a}}o Carvalho and Dorothea Koert and Marek Daniv and Jan Peters}, title = {Residual Robot Learning for Object-Centric Probabilistic Movement Primitives}, journal = {CoRR}, volume = {abs/2203.03918}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.03918}, doi = {10.48550/ARXIV.2203.03918}, eprinttype = {arXiv}, eprint = {2203.03918}, timestamp = {Tue, 20 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-03918.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-03919, author = {Jascha Hellwig and Mark Baierl and Jo{\~{a}}o Carvalho and Julen Urain and Jan Peters}, title = {A Hierarchical Approach to Active Pose Estimation}, journal = {CoRR}, volume = {abs/2203.03919}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.03919}, doi = {10.48550/ARXIV.2203.03919}, eprinttype = {arXiv}, eprint = {2203.03919}, timestamp = {Tue, 20 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-03919.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-04051, author = {Snehal Jauhri and Jan Peters and Georgia Chalvatzaki}, title = {Robot Learning of Mobile Manipulation with Reachability Behavior Priors}, journal = {CoRR}, volume = {abs/2203.04051}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.04051}, doi = {10.48550/ARXIV.2203.04051}, eprinttype = {arXiv}, eprint = {2203.04051}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-04051.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-04120, author = {Niklas Funk and Svenja Menzenbach and Georgia Chalvatzaki and Jan Peters}, title = {Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery}, journal = {CoRR}, volume = {abs/2203.04120}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.04120}, doi = {10.48550/ARXIV.2203.04120}, eprinttype = {arXiv}, eprint = {2203.04120}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-04120.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-04739, author = {Puze Liu and Kuo Zhang and Davide Tateo and Snehal Jauhri and Jan Peters and Georgia Chalvatzaki}, title = {Regularized Deep Signed Distance Fields for Reactive Motion Generation}, journal = {CoRR}, volume = {abs/2203.04739}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.04739}, doi = {10.48550/ARXIV.2203.04739}, eprinttype = {arXiv}, eprint = {2203.04739}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-04739.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-04791, author = {Marius Memmel and Puze Liu and Davide Tateo and Jan Peters}, title = {Dimensionality Reduction and Prioritized Exploration for Policy Search}, journal = {CoRR}, volume = {abs/2203.04791}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.04791}, doi = {10.48550/ARXIV.2203.04791}, eprinttype = {arXiv}, eprint = {2203.04791}, timestamp = {Wed, 16 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-04791.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-10568, author = {Lei Xu and Tianyu Ren and Georgia Chalvatzaki and Jan Peters}, title = {Accelerating Integrated Task and Motion Planning with Neural Feasibility Checking}, journal = {CoRR}, volume = {abs/2203.10568}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.10568}, doi = {10.48550/ARXIV.2203.10568}, eprinttype = {arXiv}, eprint = {2203.10568}, timestamp = {Tue, 29 Mar 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-10568.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2203-14660, author = {Daniel Palenicek and Michael Lutter and Jan Peters}, title = {Revisiting Model-based Value Expansion}, journal = {CoRR}, volume = {abs/2203.14660}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2203.14660}, doi = {10.48550/ARXIV.2203.14660}, eprinttype = {arXiv}, eprint = {2203.14660}, timestamp = {Mon, 04 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2203-14660.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2204-05369, author = {Alexander Lambert and An T. Le and Julen Urain and Georgia Chalvatzaki and Byron Boots and Jan Peters}, title = {Learning Implicit Priors for Motion Optimization}, journal = {CoRR}, volume = {abs/2204.05369}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2204.05369}, doi = {10.48550/ARXIV.2204.05369}, eprinttype = {arXiv}, eprint = {2204.05369}, timestamp = {Tue, 03 May 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2204-05369.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2206-10313, author = {Tim Schneider and Boris Belousov and Hany Abdulsamad and Jan Peters}, title = {Active Inference for Robotic Manipulation}, journal = {CoRR}, volume = {abs/2206.10313}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2206.10313}, doi = {10.48550/ARXIV.2206.10313}, eprinttype = {arXiv}, eprint = {2206.10313}, timestamp = {Mon, 27 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2206-10313.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2207-01414, author = {Kai Ploeger and Jan Peters}, title = {Controlling the Cascade: Kinematic Planning for N-ball Toss Juggling}, journal = {CoRR}, volume = {abs/2207.01414}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2207.01414}, doi = {10.48550/ARXIV.2207.01414}, eprinttype = {arXiv}, eprint = {2207.01414}, timestamp = {Wed, 06 Jul 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2207-01414.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2208-02673, author = {Tuan Dam and Georgia Chalvatzaki and Jan Peters and Joni Pajarinen}, title = {Monte-Carlo Robot Path Planning}, journal = {CoRR}, volume = {abs/2208.02673}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2208.02673}, doi = {10.48550/ARXIV.2208.02673}, eprinttype = {arXiv}, eprint = {2208.02673}, timestamp = {Wed, 10 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2208-02673.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2209-03855, author = {Julen Urain and Niklas Funk and Jan Peters and Georgia Chalvatzaki}, title = {SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion}, journal = {CoRR}, volume = {abs/2209.03855}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2209.03855}, doi = {10.48550/ARXIV.2209.03855}, eprinttype = {arXiv}, eprint = {2209.03855}, timestamp = {Tue, 27 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2209-03855.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2209-04698, author = {Alexander I. Cowen{-}Rivers and Philip John Gorinski and Aivar Sootla and Asif Khan and Furui Liu and Jun Wang and Jan Peters and Haitham Bou{-}Ammar}, title = {Structured Q-learning For Antibody Design}, journal = {CoRR}, volume = {abs/2209.04698}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2209.04698}, doi = {10.48550/ARXIV.2209.04698}, eprinttype = {arXiv}, eprint = {2209.04698}, timestamp = {Thu, 05 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2209-04698.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2209-05333, author = {Bang You and Jingming Xie and Youping Chen and Jan Peters and Oleg Arenz}, title = {Self-supervised Sequential Information Bottleneck for Robust Exploration in Deep Reinforcement Learning}, journal = {CoRR}, volume = {abs/2209.05333}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2209.05333}, doi = {10.48550/ARXIV.2209.05333}, eprinttype = {arXiv}, eprint = {2209.05333}, timestamp = {Tue, 27 Sep 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2209-05333.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2209-13308, author = {Puze Liu and Kuo Zhang and Davide Tateo and Snehal Jauhri and Zhiyuan Hu and Jan Peters and Georgia Chalvatzaki}, title = {Safe reinforcement learning of dynamic high-dimensional robotic tasks: navigation, manipulation, interaction}, journal = {CoRR}, volume = {abs/2209.13308}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2209.13308}, doi = {10.48550/ARXIV.2209.13308}, eprinttype = {arXiv}, eprint = {2209.13308}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2209-13308.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-02054, author = {Luca Lach and Niklas Funk and Robert Haschke and S{\'{e}}verin Lemaignan and Helge Joachim Ritter and Jan Peters and Georgia Chalvatzaki}, title = {Placing by Touching: An empirical study on the importance of tactile sensing for precise object placing}, journal = {CoRR}, volume = {abs/2210.02054}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.02054}, doi = {10.48550/ARXIV.2210.02054}, eprinttype = {arXiv}, eprint = {2210.02054}, timestamp = {Fri, 07 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-02054.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-03512, author = {Joe Watson and Jan Peters}, title = {Inferring Smooth Control: Monte Carlo Posterior Policy Iteration with Gaussian Processes}, journal = {CoRR}, volume = {abs/2210.03512}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.03512}, doi = {10.48550/ARXIV.2210.03512}, eprinttype = {arXiv}, eprint = {2210.03512}, timestamp = {Wed, 12 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-03512.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-07890, author = {Kay Hansel and Julen Urain and Jan Peters and Georgia Chalvatzaki}, title = {Hierarchical Policy Blending as Inference for Reactive Robot Control}, journal = {CoRR}, volume = {abs/2210.07890}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.07890}, doi = {10.48550/ARXIV.2210.07890}, eprinttype = {arXiv}, eprint = {2210.07890}, timestamp = {Wed, 07 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-07890.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-12418, author = {Vignesh Prasad and Dorothea Koert and Ruth Stock{-}Homburg and Jan Peters and Georgia Chalvatzaki}, title = {{MILD:} Multimodal Interactive Latent Dynamics for Learning Human-Robot Interaction}, journal = {CoRR}, volume = {abs/2210.12418}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.12418}, doi = {10.48550/ARXIV.2210.12418}, eprinttype = {arXiv}, eprint = {2210.12418}, timestamp = {Fri, 28 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-12418.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2210-12806, author = {Tim Schneider and Boris Belousov and Georgia Chalvatzaki and Diego Romeres and Devesh K. Jha and Jan Peters}, title = {Active Exploration for Robotic Manipulation}, journal = {CoRR}, volume = {abs/2210.12806}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2210.12806}, doi = {10.48550/ARXIV.2210.12806}, eprinttype = {arXiv}, eprint = {2210.12806}, timestamp = {Fri, 28 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2210-12806.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-01120, author = {Hany Abdulsamad and Peter Nickl and Pascal Klink and Jan Peters}, title = {Variational Hierarchical Mixtures for Learning Probabilistic Inverse Dynamics}, journal = {CoRR}, volume = {abs/2211.01120}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.01120}, doi = {10.48550/ARXIV.2211.01120}, eprinttype = {arXiv}, eprint = {2211.01120}, timestamp = {Fri, 04 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-01120.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-14655, author = {Max Siebenborn and Boris Belousov and Junning Huang and Jan Peters}, title = {How Crucial is Transformer in Decision Transformer?}, journal = {CoRR}, volume = {abs/2211.14655}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.14655}, doi = {10.48550/ARXIV.2211.14655}, eprinttype = {arXiv}, eprint = {2211.14655}, timestamp = {Tue, 29 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-14655.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2211-16110, author = {Hamish Flynn and David Reeb and Melih Kandemir and Jan Peters}, title = {PAC-Bayes Bounds for Bandit Problems: {A} Survey and Experimental Comparison}, journal = {CoRR}, volume = {abs/2211.16110}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2211.16110}, doi = {10.48550/ARXIV.2211.16110}, eprinttype = {arXiv}, eprint = {2211.16110}, timestamp = {Fri, 02 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2211-16110.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-01938, author = {An T. Le and Kay Hansel and Jan Peters and Georgia Chalvatzaki}, title = {Hierarchical Policy Blending As Optimal Transport}, journal = {CoRR}, volume = {abs/2212.01938}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.01938}, doi = {10.48550/ARXIV.2212.01938}, eprinttype = {arXiv}, eprint = {2212.01938}, timestamp = {Thu, 08 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-01938.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-04914, author = {Alessandro G. Bottero and Carlos E. Luis and Julia Vinogradska and Felix Berkenkamp and Jan Peters}, title = {Information-Theoretic Safe Exploration with Gaussian Processes}, journal = {CoRR}, volume = {abs/2212.04914}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.04914}, doi = {10.48550/ARXIV.2212.04914}, eprinttype = {arXiv}, eprint = {2212.04914}, timestamp = {Mon, 02 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-04914.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2212-13007, author = {Yaonan Zhu and Shukrullo Nazirjonov and Bingheng Jiang and Jacinto E. Colan Zaita and Tadayoshi Aoyama and Yasuhisa Hasegawa and Boris Belousov and Kay Hansel and Jan Peters}, title = {Visual Tactile Sensor Based Force Estimation for Position-Force Teleoperation}, journal = {CoRR}, volume = {abs/2212.13007}, year = {2022}, url = {https://doi.org/10.48550/arXiv.2212.13007}, doi = {10.48550/ARXIV.2212.13007}, eprinttype = {arXiv}, eprint = {2212.13007}, timestamp = {Wed, 04 Jan 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2212-13007.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/RawalKTKPS21, author = {Niyati Rawal and Dorothea Koert and Cigdem Turan and Kristian Kersting and Jan Peters and Ruth Stock{-}Homburg}, title = {ExGenNet: Learning to Generate Robotic Facial Expression Using Facial Expression Recognition}, journal = {Frontiers Robotics {AI}}, volume = {8}, pages = {730317}, year = {2021}, url = {https://doi.org/10.3389/frobt.2021.730317}, doi = {10.3389/FROBT.2021.730317}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/firai/RawalKTKPS21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/DEramoTBRP21, author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters}, title = {MushroomRL: Simplifying Reinforcement Learning Research}, journal = {J. Mach. Learn. Res.}, volume = {22}, pages = {131:1--131:5}, year = {2021}, url = {http://jmlr.org/papers/v22/18-056.html}, timestamp = {Mon, 31 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jmlr/DEramoTBRP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/KlinkABDPP21, author = {Pascal Klink and Hany Abdulsamad and Boris Belousov and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning}, journal = {J. Mach. Learn. Res.}, volume = {22}, pages = {182:1--182:52}, year = {2021}, url = {http://jmlr.org/papers/v22/21-0112.html}, timestamp = {Mon, 31 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jmlr/KlinkABDPP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/DEramoCNPAPR21, author = {Carlo D'Eramo and Andrea Cini and Alessandro Nuara and Matteo Pirotta and Cesare Alippi and Jan Peters and Marcello Restelli}, title = {Gaussian Approximation for Bias Reduction in Q-Learning}, journal = {J. Mach. Learn. Res.}, volume = {22}, pages = {277:1--277:51}, year = {2021}, url = {http://jmlr.org/papers/v22/20-633.html}, timestamp = {Mon, 31 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jmlr/DEramoCNPAPR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/AkrourAP21, author = {Riad Akrour and Asma Atamna and Jan Peters}, title = {Convex optimization with an interpolation-based projection and its application to deep learning}, journal = {Mach. Learn.}, volume = {110}, number = {8}, pages = {2267--2289}, year = {2021}, url = {https://doi.org/10.1007/s10994-021-06037-z}, doi = {10.1007/S10994-021-06037-Z}, timestamp = {Wed, 01 Sep 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ml/AkrourAP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/MuratoreG021, author = {Fabio Muratore and Michael Gienger and Jan Peters}, title = {Assessing Transferability From Simulation to Reality for Reinforcement Learning}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {43}, number = {4}, pages = {1172--1183}, year = {2021}, url = {https://doi.org/10.1109/TPAMI.2019.2952353}, doi = {10.1109/TPAMI.2019.2952353}, timestamp = {Tue, 01 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/MuratoreG021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/MuratoreEGP21, author = {Fabio Muratore and Christian Eilers and Michael Gienger and Jan Peters}, title = {Data-Efficient Domain Randomization With Bayesian Optimization}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {6}, number = {2}, pages = {911--918}, year = {2021}, url = {https://doi.org/10.1109/LRA.2021.3052391}, doi = {10.1109/LRA.2021.3052391}, timestamp = {Tue, 02 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/MuratoreEGP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/TannebergPRP21, author = {Daniel Tanneberg and Kai Ploeger and Elmar Rueckert and Jan Peters}, title = {{SKID} {RAW:} Skill Discovery From Raw Trajectories}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {6}, number = {3}, pages = {4696--4703}, year = {2021}, url = {https://doi.org/10.1109/LRA.2021.3068891}, doi = {10.1109/LRA.2021.3068891}, timestamp = {Thu, 29 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/TannebergPRP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tase/HoferBHGMGAFGLL21, author = {Sebastian H{\"{o}}fer and Kostas E. Bekris and Ankur Handa and Juan Camilo Gamboa and Melissa Mozifian and Florian Golemo and Christopher G. Atkeson and Dieter Fox and Ken Goldberg and John Leonard and C. Karen Liu and Jan Peters and Shuran Song and Peter Welinder and Martha White}, title = {Sim2Real in Robotics and Automation: Applications and Challenges}, journal = {{IEEE} Trans Autom. Sci. Eng.}, volume = {18}, number = {2}, pages = {398--400}, year = {2021}, url = {https://doi.org/10.1109/TASE.2021.3064065}, doi = {10.1109/TASE.2021.3064065}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/tase/HoferBHGMGAFGLL21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/thms/Bustamante0SGJ21, author = {Samuel Bustamante and Jan Peters and Bernhard Sch{\"{o}}lkopf and Moritz Grosse{-}Wentrup and Vinay Jayaram}, title = {ArmSym: {A} Virtual Human-Robot Interaction Laboratory for Assistive Robotics}, journal = {{IEEE} Trans. Hum. Mach. Syst.}, volume = {51}, number = {6}, pages = {568--577}, year = {2021}, url = {https://doi.org/10.1109/THMS.2021.3106865}, doi = {10.1109/THMS.2021.3106865}, timestamp = {Wed, 15 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/thms/Bustamante0SGJ21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aimech/StuhlenmillerCR21, author = {Florian Stuhlenmiller and Debora Clever and Stephan Rinderknecht and Michael Lutter and Jan Peters}, title = {Trajectory Optimization of Energy Consumption and Expected Service Life of a Robotic System}, booktitle = {{IEEE/ASME} International Conference on Advanced Intelligent Mechatronics, {AIM} 2021, Delft, The Netherlands, July 12-16, 2021}, pages = {842--847}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/AIM46487.2021.9517539}, doi = {10.1109/AIM46487.2021.9517539}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aimech/StuhlenmillerCR21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/WatsonLKP021, author = {Joe Watson and Jihao Andreas Lin and Pascal Klink and Joni Pajarinen and Jan Peters}, editor = {Arindam Banerjee and Kenji Fukumizu}, title = {Latent Derivative Bayesian Last Layer Networks}, booktitle = {The 24th International Conference on Artificial Intelligence and Statistics, {AISTATS} 2021, April 13-15, 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {130}, pages = {1198--1206}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v130/watson21a.html}, timestamp = {Wed, 14 Apr 2021 16:51:37 +0200}, biburl = {https://dblp.org/rec/conf/aistats/WatsonLKP021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/Watson021, author = {Joe Watson and Jan Peters}, title = {Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk}, booktitle = {2021 American Control Conference, {ACC} 2021, New Orleans, LA, USA, May 25-28, 2021}, pages = {1231--1236}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.23919/ACC50511.2021.9482657}, doi = {10.23919/ACC50511.2021.9482657}, timestamp = {Fri, 30 Jul 2021 11:11:12 +0200}, biburl = {https://dblp.org/rec/conf/amcc/Watson021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/case/LutterCKLP21, author = {Michael Lutter and Debora Clever and Ren{\'{e}} Kirsten and Kim Listmann and Jan Peters}, title = {Building Skill Learning Systems for Robotics}, booktitle = {17th {IEEE} International Conference on Automation Science and Engineering, {CASE} 2021, Lyon, France, August 23-27, 2021}, pages = {1878--1883}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/CASE49439.2021.9551562}, doi = {10.1109/CASE49439.2021.9551562}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/case/LutterCKLP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/LiuTB021, author = {Puze Liu and Davide Tateo and Haitham Bou{-}Ammar and Jan Peters}, editor = {Aleksandra Faust and David Hsu and Gerhard Neumann}, title = {Robot Reinforcement Learning on the Constraint Manifold}, booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}}, series = {Proceedings of Machine Learning Research}, volume = {164}, pages = {1357--1366}, publisher = {{PMLR}}, year = {2021}, url = {https://proceedings.mlr.press/v164/liu22c.html}, timestamp = {Wed, 19 Jan 2022 17:10:33 +0100}, biburl = {https://dblp.org/rec/conf/corl/LiuTB021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/FunkCB021, author = {Niklas Funk and Georgia Chalvatzaki and Boris Belousov and Jan Peters}, editor = {Aleksandra Faust and David Hsu and Gerhard Neumann}, title = {Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction}, booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}}, series = {Proceedings of Machine Learning Research}, volume = {164}, pages = {1401--1411}, publisher = {{PMLR}}, year = {2021}, url = {https://proceedings.mlr.press/v164/funk22a.html}, timestamp = {Wed, 19 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/corl/FunkCB021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/MuratoreGWBG021, author = {Fabio Muratore and Theo Gruner and Florian Wiese and Boris Belousov and Michael Gienger and Jan Peters}, editor = {Aleksandra Faust and David Hsu and Gerhard Neumann}, title = {Neural Posterior Domain Randomization}, booktitle = {Conference on Robot Learning, 8-11 November 2021, London, {UK}}, series = {Proceedings of Machine Learning Research}, volume = {164}, pages = {1532--1542}, publisher = {{PMLR}}, year = {2021}, url = {https://proceedings.mlr.press/v164/muratore22a.html}, timestamp = {Wed, 19 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/corl/MuratoreGWBG021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/DamD0P21, author = {Tuan Dam and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, editor = {Marina Meila and Tong Zhang}, title = {Convex Regularization in Monte-Carlo Tree Search}, booktitle = {Proceedings of the 38th International Conference on Machine Learning, {ICML} 2021, 18-24 July 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {139}, pages = {2365--2375}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v139/dam21a.html}, timestamp = {Wed, 25 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/DamD0P21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/LutterM0FG21, author = {Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg}, editor = {Marina Meila and Tong Zhang}, title = {Value Iteration in Continuous Actions, States and Time}, booktitle = {Proceedings of the 38th International Conference on Machine Learning, {ICML} 2021, 18-24 July 2021, Virtual Event}, series = {Proceedings of Machine Learning Research}, volume = {139}, pages = {7224--7234}, publisher = {{PMLR}}, year = {2021}, url = {http://proceedings.mlr.press/v139/lutter21a.html}, timestamp = {Wed, 25 Aug 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icml/LutterM0FG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LiC0W21, author = {Qin Li and Georgia Chalvatzaki and Jan Peters and Yong Wang}, title = {Directed Acyclic Graph Neural Network for Human Motion Prediction}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {3197--3204}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9561540}, doi = {10.1109/ICRA48506.2021.9561540}, timestamp = {Fri, 25 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/LiC0W21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/PrasadS021, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, title = {Learning Human-like Hand Reaching for Human-Robot Handshaking}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {3612--3618}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9560746}, doi = {10.1109/ICRA48506.2021.9560746}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/PrasadS021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LutterSW021, author = {Michael Lutter and Johannes Silberbauer and Joe Watson and Jan Peters}, title = {Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {4163--4170}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9561805}, doi = {10.1109/ICRA48506.2021.9561805}, timestamp = {Fri, 22 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/LutterSW021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/AbdulsamadNK021, author = {Hany Abdulsamad and Peter Nickl and Pascal Klink and Jan Peters}, title = {A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {4216--4222}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9560832}, doi = {10.1109/ICRA48506.2021.9560832}, timestamp = {Fri, 22 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/AbdulsamadNK021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/MorganNCDD021, author = {Andrew S. Morgan and Daljeet Nandha and Georgia Chalvatzaki and Carlo D'Eramo and Aaron M. Dollar and Jan Peters}, title = {Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {6672--6678}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9561298}, doi = {10.1109/ICRA48506.2021.9561298}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/MorganNCDD021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/TosattoC021, author = {Samuele Tosatto and Georgia Chalvatzaki and Jan Peters}, title = {Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2021, Xi'an, China, May 30 - June 5, 2021}, pages = {10815--10821}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/ICRA48506.2021.9561870}, doi = {10.1109/ICRA48506.2021.9561870}, timestamp = {Mon, 25 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/TosattoC021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/CarvalhoTMP21, author = {Jo{\~{a}}o Carvalho and Davide Tateo and Fabio Muratore and Jan Peters}, title = {An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients}, booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2021, Shenzhen, China, July 18-22, 2021}, pages = {1--10}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/IJCNN52387.2021.9533642}, doi = {10.1109/IJCNN52387.2021.9533642}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/CarvalhoTMP21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LiuTB021, author = {Puze Liu and Davide Tateo and Haitham Bou{-}Ammar and Jan Peters}, title = {Efficient and Reactive Planning for High Speed Robot Air Hockey}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2021, Prague, Czech Republic, September 27 - Oct. 1, 2021}, pages = {586--593}, publisher = {{IEEE}}, year = {2021}, url = {https://doi.org/10.1109/IROS51168.2021.9636263}, doi = {10.1109/IROS51168.2021.9636263}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LiuTB021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BauerWWBSGSAJBA21, author = {Stefan Bauer and Manuel W{\"{u}}thrich and Felix Widmaier and Annika Buchholz and Sebastian Stark and Anirudh Goyal and Thomas Steinbrenner and Joel Akpo and Shruti Joshi and Vincent Berenz and Vaibhav Agrawal and Niklas Funk and Julen Urain De Jesus and Jan Peters and Joe Watson and Claire Chen and Krishnan Srinivasan and Junwu Zhang and Jeffrey Zhang and Matthew R. Walter and Rishabh Madan and Takuma Yoneda and Denis Yarats and Arthur Allshire and Ethan K. Gordon and Tapomayukh Bhattacharjee and Siddhartha S. Srinivasa and Animesh Garg and Takahiro Maeda and Harshit Sikchi and Jilong Wang and Qingfeng Yao and Shuyu Yang and Robert McCarthy and Francisco Roldan Sanchez and Qiang Wang and David Cordova Bulens and Kevin McGuinness and Noel E. O'Connor and Stephen J. Redmond and Bernhard Sch{\"{o}}lkopf}, editor = {Douwe Kiela and Marco Ciccone and Barbara Caputo}, title = {Real Robot Challenge: {A} Robotics Competition in the Cloud}, booktitle = {NeurIPS 2021 Competitions and Demonstrations Track, 6-14 December 2021, Online}, series = {Proceedings of Machine Learning Research}, volume = {176}, pages = {190--204}, publisher = {{PMLR}}, year = {2021}, url = {https://proceedings.mlr.press/v176/bauer22a.html}, timestamp = {Mon, 06 Feb 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/BauerWWBSGSAJBA21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/LutterM0FG21, author = {Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg}, editor = {Dylan A. Shell and Marc Toussaint and M. Ani Hsieh}, title = {Robust Value Iteration for Continuous Control Tasks}, booktitle = {Robotics: Science and Systems XVII, Virtual Event, July 12-16, 2021}, year = {2021}, url = {https://doi.org/10.15607/RSS.2021.XVII.007}, doi = {10.15607/RSS.2021.XVII.007}, timestamp = {Wed, 21 Jul 2021 17:07:17 +0200}, biburl = {https://dblp.org/rec/conf/rss/LutterM0FG21.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/UrainLLD021, author = {Julen Urain and Puze Liu and Anqi Li and Carlo D'Eramo and Jan Peters}, editor = {Dylan A. Shell and Marc Toussaint and M. Ani Hsieh}, title = {Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning}, booktitle = {Robotics: Science and Systems XVII, Virtual Event, July 12-16, 2021}, year = {2021}, url = {https://doi.org/10.15607/RSS.2021.XVII.052}, doi = {10.15607/RSS.2021.XVII.052}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/rss/UrainLLD021.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2102-07193, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, title = {Human-Robot Handshaking: {A} Review}, journal = {CoRR}, volume = {abs/2102.07193}, year = {2021}, url = {https://arxiv.org/abs/2102.07193}, eprinttype = {arXiv}, eprint = {2102.07193}, timestamp = {Thu, 18 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2102-07193.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2102-13176, author = {Pascal Klink and Hany Abdulsamad and Boris Belousov and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {A Probabilistic Interpretation of Self-Paced Learning with Applications to Reinforcement Learning}, journal = {CoRR}, volume = {abs/2102.13176}, year = {2021}, url = {https://arxiv.org/abs/2102.13176}, eprinttype = {arXiv}, eprint = {2102.13176}, timestamp = {Tue, 02 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2102-13176.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-00616, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, title = {Learning Human-like Hand Reaching for Human-Robot Handshaking}, journal = {CoRR}, volume = {abs/2103.00616}, year = {2021}, url = {https://arxiv.org/abs/2103.00616}, eprinttype = {arXiv}, eprint = {2103.00616}, timestamp = {Thu, 04 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-00616.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-05456, author = {Tianyu Ren and Georgia Chalvatzaki and Jan Peters}, title = {Extended Task and Motion Planning of Long-horizon Robot Manipulation}, journal = {CoRR}, volume = {abs/2103.05456}, year = {2021}, url = {https://arxiv.org/abs/2103.05456}, eprinttype = {arXiv}, eprint = {2103.05456}, timestamp = {Mon, 15 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-05456.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-06319, author = {Joe Watson and Jan Peters}, title = {Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk}, journal = {CoRR}, volume = {abs/2103.06319}, year = {2021}, url = {https://arxiv.org/abs/2103.06319}, eprinttype = {arXiv}, eprint = {2103.06319}, timestamp = {Tue, 16 Mar 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-06319.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-13842, author = {Andrew S. Morgan and Daljeet Nandha and Georgia Chalvatzaki and Carlo D'Eramo and Aaron M. Dollar and Jan Peters}, title = {Model Predictive Actor-Critic: Accelerating Robot Skill Acquisition with Deep Reinforcement Learning}, journal = {CoRR}, volume = {abs/2103.13842}, year = {2021}, url = {https://arxiv.org/abs/2103.13842}, eprinttype = {arXiv}, eprint = {2103.13842}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-13842.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-14610, author = {Daniel Tanneberg and Kai Ploeger and Elmar Rueckert and Jan Peters}, title = {{SKID} {RAW:} Skill Discovery from Raw Trajectories}, journal = {CoRR}, volume = {abs/2103.14610}, year = {2021}, url = {https://arxiv.org/abs/2103.14610}, eprinttype = {arXiv}, eprint = {2103.14610}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-14610.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2103-15388, author = {Hany Abdulsamad and Tim Dorau and Boris Belousov and Jia{-}Jie Zhu and Jan Peters}, title = {Distributionally Robust Trajectory Optimization Under Uncertain Dynamics via Relative-Entropy Trust Regions}, journal = {CoRR}, volume = {abs/2103.15388}, year = {2021}, url = {https://arxiv.org/abs/2103.15388}, eprinttype = {arXiv}, eprint = {2103.15388}, timestamp = {Wed, 07 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2103-15388.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2104-10986, author = {Stephan Weigand and Pascal Klink and Jan Peters and Joni Pajarinen}, title = {Reinforcement Learning using Guided Observability}, journal = {CoRR}, volume = {abs/2104.10986}, year = {2021}, url = {https://arxiv.org/abs/2104.10986}, eprinttype = {arXiv}, eprint = {2104.10986}, timestamp = {Tue, 27 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2104-10986.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-02087, author = {Niklas Funk and Charles B. Schaff and Rishabh Madan and Takuma Yoneda and Julen Urain De Jesus and Joe Watson and Ethan K. Gordon and Felix Widmaier and Stefan Bauer and Siddhartha S. Srinivasa and Tapomayukh Bhattacharjee and Matthew R. Walter and Jan Peters}, title = {Benchmarking Structured Policies and Policy Optimization for Real-World Dexterous Object Manipulation}, journal = {CoRR}, volume = {abs/2105.02087}, year = {2021}, url = {https://arxiv.org/abs/2105.02087}, eprinttype = {arXiv}, eprint = {2105.02087}, timestamp = {Wed, 12 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-02087.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-04682, author = {Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg}, title = {Value Iteration in Continuous Actions, States and Time}, journal = {CoRR}, volume = {abs/2105.04682}, year = {2021}, url = {https://arxiv.org/abs/2105.04682}, eprinttype = {arXiv}, eprint = {2105.04682}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-04682.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-04962, author = {Julen Urain and Anqi Li and Puze Liu and Carlo D'Eramo and Jan Peters}, title = {Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning}, journal = {CoRR}, volume = {abs/2105.04962}, year = {2021}, url = {https://arxiv.org/abs/2105.04962}, eprinttype = {arXiv}, eprint = {2105.04962}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-04962.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-07693, author = {Joe Watson and Hany Abdulsamad and Rolf Findeisen and Jan Peters}, title = {Stochastic Control through Approximate Bayesian Input Inference}, journal = {CoRR}, volume = {abs/2105.07693}, year = {2021}, url = {https://arxiv.org/abs/2105.07693}, eprinttype = {arXiv}, eprint = {2105.07693}, timestamp = {Tue, 18 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-07693.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-07957, author = {Daniel Tanneberg and Elmar Rueckert and Jan Peters}, title = {Evolutionary Training and Abstraction Yields Algorithmic Generalization of Neural Computers}, journal = {CoRR}, volume = {abs/2105.07957}, year = {2021}, url = {https://arxiv.org/abs/2105.07957}, eprinttype = {arXiv}, eprint = {2105.07957}, timestamp = {Tue, 18 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-07957.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2105-12189, author = {Michael Lutter and Shie Mannor and Jan Peters and Dieter Fox and Animesh Garg}, title = {Robust Value Iteration for Continuous Control Tasks}, journal = {CoRR}, volume = {abs/2105.12189}, year = {2021}, url = {https://arxiv.org/abs/2105.12189}, eprinttype = {arXiv}, eprint = {2105.12189}, timestamp = {Tue, 01 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2105-12189.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2106-03609, author = {Antoine Grosnit and Rasul Tutunov and Alexandre Max Maraval and Ryan{-}Rhys Griffiths and Alexander I. Cowen{-}Rivers and Lin Yang and Lin Zhu and Wenlong Lyu and Zhitang Chen and Jun Wang and Jan Peters and Haitham Bou{-}Ammar}, title = {High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning}, journal = {CoRR}, volume = {abs/2106.03609}, year = {2021}, url = {https://arxiv.org/abs/2106.03609}, eprinttype = {arXiv}, eprint = {2106.03609}, timestamp = {Thu, 10 Nov 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2106-03609.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-06140, author = {Puze Liu and Davide Tateo and Haitham Bou{-}Ammar and Jan Peters}, title = {Efficient and Reactive Planning for High Speed Robot Air Hockey}, journal = {CoRR}, volume = {abs/2107.06140}, year = {2021}, url = {https://arxiv.org/abs/2107.06140}, eprinttype = {arXiv}, eprint = {2107.06140}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-06140.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2107-09359, author = {Jo{\~{a}}o Carvalho and Davide Tateo and Fabio Muratore and Jan Peters}, title = {An Empirical Analysis of Measure-Valued Derivatives for Policy Gradients}, journal = {CoRR}, volume = {abs/2107.09359}, year = {2021}, url = {https://arxiv.org/abs/2107.09359}, eprinttype = {arXiv}, eprint = {2107.09359}, timestamp = {Thu, 29 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2107-09359.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2109-10957, author = {Stefan Bauer and Felix Widmaier and Manuel W{\"{u}}thrich and Niklas Funk and Julen Urain De Jesus and Jan Peters and Joe Watson and Claire Chen and Krishnan Srinivasan and Junwu Zhang and Jeffrey Zhang and Matthew R. Walter and Rishabh Madan and Charles B. Schaff and Takahiro Maeda and Takuma Yoneda and Denis Yarats and Arthur Allshire and Ethan K. Gordon and Tapomayukh Bhattacharjee and Siddhartha S. Srinivasa and Animesh Garg and Annika Buchholz and Sebastian Stark and Thomas Steinbrenner and Joel Akpo and Shruti Joshi and Vaibhav Agrawal and Bernhard Sch{\"{o}}lkopf}, title = {A Robot Cluster for Reproducible Research in Dexterous Manipulation}, journal = {CoRR}, volume = {abs/2109.10957}, year = {2021}, url = {https://arxiv.org/abs/2109.10957}, eprinttype = {arXiv}, eprint = {2109.10957}, timestamp = {Mon, 05 Dec 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2109-10957.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-01894, author = {Michael Lutter and Jan Peters}, title = {Combining Physics and Deep Learning to learn Continuous-Time Dynamics Models}, journal = {CoRR}, volume = {abs/2110.01894}, year = {2021}, url = {https://arxiv.org/abs/2110.01894}, eprinttype = {arXiv}, eprint = {2110.01894}, timestamp = {Fri, 08 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-01894.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-01954, author = {Michael Lutter and Boris Belousov and Shie Mannor and Dieter Fox and Animesh Garg and Jan Peters}, title = {Continuous-Time Fitted Value Iteration for Robust Policies}, journal = {CoRR}, volume = {abs/2110.01954}, year = {2021}, url = {https://arxiv.org/abs/2110.01954}, eprinttype = {arXiv}, eprint = {2110.01954}, timestamp = {Fri, 08 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-01954.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-11774, author = {Julen Urain and Davide Tateo and Jan Peters}, title = {Learning Stable Vector Fields on Lie Groups}, journal = {CoRR}, volume = {abs/2110.11774}, year = {2021}, url = {https://arxiv.org/abs/2110.11774}, eprinttype = {arXiv}, eprint = {2110.11774}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-11774.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2110-12422, author = {Michael Lutter and Johannes Silberbauer and Joe Watson and Jan Peters}, title = {A Differentiable Newton-Euler Algorithm for Real-World Robotics}, journal = {CoRR}, volume = {abs/2110.12422}, year = {2021}, url = {https://arxiv.org/abs/2110.12422}, eprinttype = {arXiv}, eprint = {2110.12422}, timestamp = {Thu, 28 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2110-12422.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-00956, author = {Fabio Muratore and Fabio Ramos and Greg Turk and Wenhao Yu and Michael Gienger and Jan Peters}, title = {Robot Learning from Randomized Simulations: {A} Review}, journal = {CoRR}, volume = {abs/2111.00956}, year = {2021}, url = {https://arxiv.org/abs/2111.00956}, eprinttype = {arXiv}, eprint = {2111.00956}, timestamp = {Tue, 18 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-00956.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2111-06211, author = {Hany Abdulsamad and Jan Peters}, title = {Model-Based Reinforcement Learning for Stochastic Hybrid Systems}, journal = {CoRR}, volume = {abs/2111.06211}, year = {2021}, url = {https://arxiv.org/abs/2111.06211}, eprinttype = {arXiv}, eprint = {2111.06211}, timestamp = {Tue, 16 Nov 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2111-06211.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2112-03149, author = {Julien Brosseit and Benedikt Hahner and Fabio Muratore and Michael Gienger and Jan Peters}, title = {Distilled Domain Randomization}, journal = {CoRR}, volume = {abs/2112.03149}, year = {2021}, url = {https://arxiv.org/abs/2112.03149}, eprinttype = {arXiv}, eprint = {2112.03149}, timestamp = {Wed, 08 Dec 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2112-03149.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/aamas/LauriPP20, author = {Mikko Lauri and Joni Pajarinen and Jan Peters}, title = {Multi-agent active information gathering in discrete and continuous-state decentralized POMDPs by policy graph improvement}, journal = {Auton. Agents Multi Agent Syst.}, volume = {34}, number = {2}, pages = {42}, year = {2020}, url = {https://doi.org/10.1007/s10458-020-09467-6}, doi = {10.1007/S10458-020-09467-6}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/aamas/LauriPP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ar/EwertonAP20, author = {Marco Ewerton and Oleg Arenz and Jan Peters}, title = {Assisted teleoperation in changing environments with a mixture of virtual guides}, journal = {Adv. Robotics}, volume = {34}, number = {18}, pages = {1157--1170}, year = {2020}, url = {https://doi.org/10.1080/01691864.2020.1785326}, doi = {10.1080/01691864.2020.1785326}, timestamp = {Fri, 14 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ar/EwertonAP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/KoertKSDP20, author = {Dorothea Koert and Maximilian Kircher and Vildan Salikutluk and Carlo D'Eramo and Jan Peters}, title = {Multi-Channel Interactive Reinforcement Learning for Sequential Tasks}, journal = {Frontiers Robotics {AI}}, volume = {7}, pages = {97}, year = {2020}, url = {https://doi.org/10.3389/frobt.2020.00097}, doi = {10.3389/FROBT.2020.00097}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/firai/KoertKSDP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/VeigaAP20, author = {Filipe Veiga and Riad Akrour and Jan Peters}, title = {Hierarchical Tactile-Based Control Decomposition of Dexterous In-Hand Manipulation Tasks}, journal = {Frontiers Robotics {AI}}, volume = {7}, pages = {521448}, year = {2020}, url = {https://doi.org/10.3389/frobt.2020.521448}, doi = {10.3389/FROBT.2020.521448}, timestamp = {Tue, 24 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/firai/VeigaAP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijhr/KoertTELP20, author = {Dorothea Koert and Susanne Trick and Marco Ewerton and Michael Lutter and Jan Peters}, title = {Incremental Learning of an Open-Ended Collaborative Skill Library}, journal = {Int. J. Humanoid Robotics}, volume = {17}, number = {1}, pages = {2050001:1--2050001:23}, year = {2020}, url = {https://doi.org/10.1142/S0219843620500012}, doi = {10.1142/S0219843620500012}, timestamp = {Fri, 22 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijhr/KoertTELP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/LioutikovMVKP20, author = {Rudolf Lioutikov and Guilherme Maeda and Filipe Veiga and Kristian Kersting and Jan Peters}, title = {Learning attribute grammars for movement primitive sequencing}, journal = {Int. J. Robotics Res.}, volume = {39}, number = {1}, year = {2020}, url = {https://doi.org/10.1177/0278364919868279}, doi = {10.1177/0278364919868279}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/LioutikovMVKP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/natmi/TannebergRP20, author = {Daniel Tanneberg and Elmar Rueckert and Jan Peters}, title = {Evolutionary training and abstraction yields algorithmic generalization of neural computers}, journal = {Nat. Mach. Intell.}, volume = {2}, number = {12}, pages = {753--763}, year = {2020}, url = {https://doi.org/10.1038/s42256-020-00255-1}, doi = {10.1038/S42256-020-00255-1}, timestamp = {Mon, 03 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/natmi/TannebergRP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/pami/VinogradskaBAKP20, author = {Julia Vinogradska and Bastian Bischoff and Jan Achterhold and Torsten Koller and Jan Peters}, title = {Numerical Quadrature for Probabilistic Policy Search}, journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.}, volume = {42}, number = {1}, pages = {164--175}, year = {2020}, url = {https://doi.org/10.1109/TPAMI.2018.2879335}, doi = {10.1109/TPAMI.2018.2879335}, timestamp = {Sat, 30 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/pami/VinogradskaBAKP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/Gomez-GonzalezP20, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Sergey Prokudin and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Real Time Trajectory Prediction Using Deep Conditional Generative Models}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {5}, number = {2}, pages = {970--976}, year = {2020}, url = {https://doi.org/10.1109/LRA.2020.2966390}, doi = {10.1109/LRA.2020.2966390}, timestamp = {Fri, 22 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/Gomez-GonzalezP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/LockelPV20, author = {Stefan L{\"{o}}ckel and Jan Peters and Peter van Vliet}, title = {A Probabilistic Framework for Imitating Human Race Driver Behavior}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {5}, number = {2}, pages = {2086--2093}, year = {2020}, url = {https://doi.org/10.1109/LRA.2020.2970620}, doi = {10.1109/LRA.2020.2970620}, timestamp = {Fri, 22 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/LockelPV20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/MotokuraTEP20, author = {Kurena Motokura and Masaki Takahashi and Marco Ewerton and Jan Peters}, title = {Plucking Motions for Tea Harvesting Robots Using Probabilistic Movement Primitives}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {5}, number = {2}, pages = {3275--3282}, year = {2020}, url = {https://doi.org/10.1109/LRA.2020.2976314}, doi = {10.1109/LRA.2020.2976314}, timestamp = {Fri, 22 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/MotokuraTEP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/LauriPPF20, author = {Mikko Lauri and Joni Pajarinen and Jan Peters and Simone Frintrop}, title = {Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {5}, number = {4}, pages = {5323--5330}, year = {2020}, url = {https://doi.org/10.1109/LRA.2020.3007445}, doi = {10.1109/LRA.2020.3007445}, timestamp = {Fri, 09 Apr 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/LauriPPF20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/PajarinenAPN20, author = {Joni Pajarinen and Oleg Arenz and Jan Peters and Gerhard Neumann}, title = {Probabilistic Approach to Physical Object Disentangling}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {5}, number = {4}, pages = {5510--5517}, year = {2020}, url = {https://doi.org/10.1109/LRA.2020.3006789}, doi = {10.1109/LRA.2020.3006789}, timestamp = {Mon, 26 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ral/PajarinenAPN20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/robotics/ManschitzGKP20, author = {Simon Manschitz and Michael Gienger and Jens Kober and Jan Peters}, title = {Learning Sequential Force Interaction Skills}, journal = {Robotics}, volume = {9}, number = {2}, pages = {45}, year = {2020}, url = {https://doi.org/10.3390/robotics9020045}, doi = {10.3390/ROBOTICS9020045}, timestamp = {Thu, 06 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/robotics/ManschitzGKP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/sensors/VeigaEP20, author = {Filipe Veiga and Benoni B. Edin and Jan Peters}, title = {Grip Stabilization through Independent Finger Tactile Feedback Control}, journal = {Sensors}, volume = {20}, number = {6}, pages = {1748}, year = {2020}, url = {https://doi.org/10.3390/s20061748}, doi = {10.3390/S20061748}, timestamp = {Sat, 30 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/sensors/VeigaEP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/Gomez-GonzalezN20, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Gerhard Neumann and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Adaptation and Robust Learning of Probabilistic Movement Primitives}, journal = {{IEEE} Trans. Robotics}, volume = {36}, number = {2}, pages = {366--379}, year = {2020}, url = {https://doi.org/10.1109/TRO.2019.2937010}, doi = {10.1109/TRO.2019.2937010}, timestamp = {Mon, 04 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/trob/Gomez-GonzalezN20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/TosattoCA020, author = {Samuele Tosatto and Jo{\~{a}}o Carvalho and Hany Abdulsamad and Jan Peters}, editor = {Silvia Chiappa and Roberto Calandra}, title = {A Nonparametric Off-Policy Policy Gradient}, booktitle = {The 23rd International Conference on Artificial Intelligence and Statistics, {AISTATS} 2020, 26-28 August 2020, Online [Palermo, Sicily, Italy]}, series = {Proceedings of Machine Learning Research}, volume = {108}, pages = {167--177}, publisher = {{PMLR}}, year = {2020}, url = {http://proceedings.mlr.press/v108/tosatto20a.html}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aistats/TosattoCA020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/PloegerL020, author = {Kai Ploeger and Michael Lutter and Jan Peters}, editor = {Jens Kober and Fabio Ramos and Claire J. Tomlin}, title = {High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards}, booktitle = {4th Conference on Robot Learning, CoRL 2020, 16-18 November 2020, Virtual Event / Cambridge, MA, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {155}, pages = {642--653}, publisher = {{PMLR}}, year = {2020}, url = {https://proceedings.mlr.press/v155/ploeger21a.html}, timestamp = {Tue, 18 Oct 2022 08:35:37 +0200}, biburl = {https://dblp.org/rec/conf/corl/PloegerL020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/hri/Stock-Homburg0S20, author = {Ruth Stock{-}Homburg and Jan Peters and Katharina Schneider and Vignesh Prasad and Lejla Nukovic}, editor = {Tony Belpaeme and James E. Young and Hatice Gunes and Laurel D. Riek}, title = {Evaluation of the Handshake Turing Test for anthropomorphic Robots}, booktitle = {Companion of the 2020 {ACM/IEEE} International Conference on Human-Robot Interaction, {HRI} 2020, Cambridge, UK, March 23-26, 2020}, pages = {456--458}, publisher = {{ACM}}, year = {2020}, url = {https://doi.org/10.1145/3371382.3378260}, doi = {10.1145/3371382.3378260}, timestamp = {Sat, 30 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/hri/Stock-Homburg0S20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/DEramoTBR020, author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters}, title = {Sharing Knowledge in Multi-Task Deep Reinforcement Learning}, booktitle = {8th International Conference on Learning Representations, {ICLR} 2020, Addis Ababa, Ethiopia, April 26-30, 2020}, publisher = {OpenReview.net}, year = {2020}, url = {https://openreview.net/forum?id=rkgpv2VFvr}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iclr/DEramoTBR020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/EilersEMBM020, author = {Christian Eilers and Jonas Eschmann and Robin Menzenbach and Boris Belousov and Fabio Muratore and Jan Peters}, title = {Underactuated Waypoint Trajectory Optimization for Light Painting Photography}, booktitle = {2020 {IEEE} International Conference on Robotics and Automation, {ICRA} 2020, Paris, France, May 31 - August 31, 2020}, pages = {1505--1510}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICRA40945.2020.9196516}, doi = {10.1109/ICRA40945.2020.9196516}, timestamp = {Mon, 28 Sep 2020 12:19:08 +0200}, biburl = {https://dblp.org/rec/conf/icra/EilersEMBM020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/ZelchPS20, author = {Christoph Zelch and Jan Peters and Oskar von Stryk}, title = {Learning Control Policies from Optimal Trajectories}, booktitle = {2020 {IEEE} International Conference on Robotics and Automation, {ICRA} 2020, Paris, France, May 31 - August 31, 2020}, pages = {2529--2535}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ICRA40945.2020.9196791}, doi = {10.1109/ICRA40945.2020.9196791}, timestamp = {Wed, 30 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/ZelchPS20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/DamKD0P20, author = {Tuan Dam and Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, editor = {Christian Bessiere}, title = {Generalized Mean Estimation in Monte-Carlo Tree Search}, booktitle = {Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, {IJCAI} 2020}, pages = {2397--2404}, publisher = {ijcai.org}, year = {2020}, url = {https://doi.org/10.24963/ijcai.2020/332}, doi = {10.24963/IJCAI.2020/332}, timestamp = {Mon, 20 Jul 2020 12:38:52 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/DamKD0P20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/UrainGT020, author = {Julen Urain and Michele Ginesi and Davide Tateo and Jan Peters}, title = {ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {5231--5237}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9341035}, doi = {10.1109/IROS45743.2020.9341035}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/UrainGT020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/RottmannKB0R20, author = {Nils Rottmann and Tjasa Kunavar and Jan Babic and Jan Peters and Elmar Rueckert}, title = {Learning Hierarchical Acquisition Functions for Bayesian Optimization}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {5490--5496}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9341335}, doi = {10.1109/IROS45743.2020.9341335}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/RottmannKB0R20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LauxA0P20, author = {Melvin Laux and Oleg Arenz and Jan Peters and Joni Pajarinen}, title = {Deep Adversarial Reinforcement Learning for Object Disentangling}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {5504--5510}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9341578}, doi = {10.1109/IROS45743.2020.9341578}, timestamp = {Tue, 16 Feb 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LauxA0P20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ZieseFPZA20, author = {Anton Ziese and Mario Daniele Fiore and Jan Peters and Uwe E. Zimmermann and J{\"{u}}rgen Adamy}, title = {Redundancy resolution under hard joint constraints: a generalized approach to rank updates}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {7447--7453}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9341581}, doi = {10.1109/IROS45743.2020.9341581}, timestamp = {Thu, 15 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/ZieseFPZA20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KellerTS020, author = {Leon Keller and Daniel Tanneberg and Svenja Stark and Jan Peters}, title = {Model-Based Quality-Diversity Search for Efficient Robot Learning}, booktitle = {{IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2020, Las Vegas, NV, USA, October 24, 2020 - January 24, 2021}, pages = {9675--9680}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/IROS45743.2020.9340794}, doi = {10.1109/IROS45743.2020.9340794}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/KellerTS020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isgteurope/SantosM0S20, author = {Allan Almeida Santos and Edwin Mora and Jan Peters and Florian Steinke}, title = {Decentralized Data-Driven Tuning of Droop Frequency Controllers}, booktitle = {{IEEE} {PES} Innovative Smart Grid Technologies Europe, {ISGT} Europe 2020, Delft, The Netherlands, October 26-28, 2020}, pages = {141--145}, publisher = {{IEEE}}, year = {2020}, url = {https://doi.org/10.1109/ISGT-Europe47291.2020.9248956}, doi = {10.1109/ISGT-EUROPE47291.2020.9248956}, timestamp = {Sun, 25 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isgteurope/SantosM0S20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iwai2/ImohiosenW020, author = {Abraham Imohiosen and Joe Watson and Jan Peters}, editor = {Tim Verbelen and Pablo Lanillos and Christopher L. Buckley and Cedric De Boom}, title = {Active Inference or Control as Inference? {A} Unifying View}, booktitle = {Active Inference - First International Workshop, {IWAI} 2020, Co-located with {ECML/PKDD} 2020, Ghent, Belgium, September 14, 2020, Proceedings}, series = {Communications in Computer and Information Science}, volume = {1326}, pages = {12--19}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-64919-7\_2}, doi = {10.1007/978-3-030-64919-7\_2}, timestamp = {Mon, 08 May 2023 14:35:45 +0200}, biburl = {https://dblp.org/rec/conf/iwai2/ImohiosenW020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/l4dc/Abdulsamad020, author = {Hany Abdulsamad and Jan Peters}, editor = {Alexandre M. Bayen and Ali Jadbabaie and George J. Pappas and Pablo A. Parrilo and Benjamin Recht and Claire J. Tomlin and Melanie N. Zeilinger}, title = {Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation}, booktitle = {Proceedings of the 2nd Annual Conference on Learning for Dynamics and Control, {L4DC} 2020, Online Event, Berkeley, CA, USA, 11-12 June 2020}, series = {Proceedings of Machine Learning Research}, volume = {120}, pages = {904--914}, publisher = {{PMLR}}, year = {2020}, url = {http://proceedings.mlr.press/v120/abdulsamad20a.html}, timestamp = {Fri, 27 Nov 2020 12:28:41 +0100}, biburl = {https://dblp.org/rec/conf/l4dc/Abdulsamad020.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KlinkD0P20, author = {Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria{-}Florina Balcan and Hsuan{-}Tien Lin}, title = {Self-Paced Deep Reinforcement Learning}, booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual}, year = {2020}, url = {https://proceedings.neurips.cc/paper/2020/hash/68a9750337a418a86fe06c1991a1d64c-Abstract.html}, timestamp = {Tue, 19 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/KlinkD0P20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/socrob/PrasadSP20, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, editor = {Alan R. Wagner and David Feil{-}Seifer and Kerstin Sophie Haring and Silvia Rossi and Thomas Emrys Williams and Hongsheng He and Shuzhi Sam Ge}, title = {Advances in Human-Robot Handshaking}, booktitle = {Social Robotics - 12th International Conference, {ICSR} 2020, Golden, CO, USA, November 14-18, 2020, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {12483}, pages = {478--489}, publisher = {Springer}, year = {2020}, url = {https://doi.org/10.1007/978-3-030-62056-1\_40}, doi = {10.1007/978-3-030-62056-1\_40}, timestamp = {Wed, 21 Dec 2022 13:24:29 +0100}, biburl = {https://dblp.org/rec/conf/socrob/PrasadSP20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/uai/Agudelo-EspanaG20, author = {Diego Agudelo{-}Espa{\~{n}}a and Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Stefan Bauer and Bernhard Sch{\"{o}}lkopf and Jan Peters}, editor = {Ryan P. Adams and Vibhav Gogate}, title = {Bayesian Online Prediction of Change Points}, booktitle = {Proceedings of the Thirty-Sixth Conference on Uncertainty in Artificial Intelligence, {UAI} 2020, virtual online, August 3-6, 2020}, series = {Proceedings of Machine Learning Research}, volume = {124}, pages = {320--329}, publisher = {{AUAI} Press}, year = {2020}, url = {http://proceedings.mlr.press/v124/agudelo-espana20a.html}, timestamp = {Wed, 16 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/uai/Agudelo-EspanaG20.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-00119, author = {Simone Parisi and Davide Tateo and Maximilian Hensel and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Long-Term Visitation Value for Deep Exploration in Sparse Reward Reinforcement Learning}, journal = {CoRR}, volume = {abs/2001.00119}, year = {2020}, url = {http://arxiv.org/abs/2001.00119}, eprinttype = {arXiv}, eprint = {2001.00119}, timestamp = {Fri, 10 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-00119.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-01102, author = {Carlo D'Eramo and Davide Tateo and Andrea Bonarini and Marcello Restelli and Jan Peters}, title = {MushroomRL: Simplifying Reinforcement Learning Research}, journal = {CoRR}, volume = {abs/2001.01102}, year = {2020}, url = {http://arxiv.org/abs/2001.01102}, eprinttype = {arXiv}, eprint = {2001.01102}, timestamp = {Fri, 10 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-01102.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-02435, author = {Samuele Tosatto and Jo{\~{a}}o Carvalho and Hany Abdulsamad and Jan Peters}, title = {A Nonparametric Offpolicy Policy Gradient}, journal = {CoRR}, volume = {abs/2001.02435}, year = {2020}, url = {http://arxiv.org/abs/2001.02435}, eprinttype = {arXiv}, eprint = {2001.02435}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-02435.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-08255, author = {Stefan L{\"{o}}ckel and Jan Peters and Peter van Vliet}, title = {A Probabilistic Framework for Imitating Human Race Driver Behavior}, journal = {CoRR}, volume = {abs/2001.08255}, year = {2020}, url = {https://arxiv.org/abs/2001.08255}, eprinttype = {arXiv}, eprint = {2001.08255}, timestamp = {Mon, 03 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-08255.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-10464, author = {Ruth Stock{-}Homburg and Jan Peters and Katharina Schneider and Vignesh Prasad and Lejla Nukovic}, title = {Evaluation of the Handshake Turing Test for anthropomorphic Robots}, journal = {CoRR}, volume = {abs/2001.10464}, year = {2020}, url = {https://arxiv.org/abs/2001.10464}, eprinttype = {arXiv}, eprint = {2001.10464}, timestamp = {Mon, 03 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-10464.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2001-10972, author = {Samuele Tosatto and Riad Akrour and Jan Peters}, title = {An Upper Bound of the Bias of Nadaraya-Watson Kernel Regression under Lipschitz Assumptions}, journal = {CoRR}, volume = {abs/2001.10972}, year = {2020}, url = {https://arxiv.org/abs/2001.10972}, eprinttype = {arXiv}, eprint = {2001.10972}, timestamp = {Thu, 30 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2001-10972.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2002-11495, author = {Joni Pajarinen and Oleg Arenz and Jan Peters and Gerhard Neumann}, title = {Probabilistic approach to physical object disentangling}, journal = {CoRR}, volume = {abs/2002.11495}, year = {2020}, url = {https://arxiv.org/abs/2002.11495}, eprinttype = {arXiv}, eprint = {2002.11495}, timestamp = {Tue, 03 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2002-11495.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-01554, author = {Christian Eilers and Jonas Eschmann and Robin Menzenbach and Boris Belousov and Fabio Muratore and Jan Peters}, title = {Underactuated Waypoint Trajectory Optimization for Light Painting Photography}, journal = {CoRR}, volume = {abs/2003.01554}, year = {2020}, url = {https://arxiv.org/abs/2003.01554}, eprinttype = {arXiv}, eprint = {2003.01554}, timestamp = {Tue, 10 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-01554.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-02471, author = {Fabio Muratore and Christian Eilers and Michael Gienger and Jan Peters}, title = {Bayesian Domain Randomization for Sim-to-Real Transfer}, journal = {CoRR}, volume = {abs/2003.02471}, year = {2020}, url = {https://arxiv.org/abs/2003.02471}, eprinttype = {arXiv}, eprint = {2003.02471}, timestamp = {Tue, 10 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-02471.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-02634, author = {Samuele Tosatto and Jonas Stadtmueller and Jan Peters}, title = {Dimensionality Reduction of Movement Primitives in Parameter Space}, journal = {CoRR}, volume = {abs/2003.02634}, year = {2020}, url = {https://arxiv.org/abs/2003.02634}, eprinttype = {arXiv}, eprint = {2003.02634}, timestamp = {Tue, 10 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-02634.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-02638, author = {Marcus Ebner von Eschenbach and Binyamin Manela and Jan Peters and Armin Biess}, title = {Metric-Based Imitation Learning Between Two Dissimilar Anthropomorphic Robotic Arms}, journal = {CoRR}, volume = {abs/2003.02638}, year = {2020}, url = {https://arxiv.org/abs/2003.02638}, eprinttype = {arXiv}, eprint = {2003.02638}, timestamp = {Fri, 13 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-02638.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-03779, author = {Melvin Laux and Oleg Arenz and Jan Peters and Joni Pajarinen}, title = {Deep Adversarial Reinforcement Learning for Object Disentangling}, journal = {CoRR}, volume = {abs/2003.03779}, year = {2020}, url = {https://arxiv.org/abs/2003.03779}, eprinttype = {arXiv}, eprint = {2003.03779}, timestamp = {Tue, 10 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-03779.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-08876, author = {Philip Becker{-}Ehmck and Maximilian Karl and Jan Peters and Patrick van der Smagt}, title = {Learning to Fly via Deep Model-Based Reinforcement Learning}, journal = {CoRR}, volume = {abs/2003.08876}, year = {2020}, url = {https://arxiv.org/abs/2003.08876}, eprinttype = {arXiv}, eprint = {2003.08876}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-08876.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2003-09280, author = {Andrea Cini and Carlo D'Eramo and Jan Peters and Cesare Alippi}, title = {Deep Reinforcement Learning with Weighted Q-Learning}, journal = {CoRR}, volume = {abs/2003.09280}, year = {2020}, url = {https://arxiv.org/abs/2003.09280}, eprinttype = {arXiv}, eprint = {2003.09280}, timestamp = {Tue, 24 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2003-09280.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2004-11812, author = {Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Self-Paced Deep Reinforcement Learning}, journal = {CoRR}, volume = {abs/2004.11812}, year = {2020}, url = {https://arxiv.org/abs/2004.11812}, eprinttype = {arXiv}, eprint = {2004.11812}, timestamp = {Tue, 28 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2004-11812.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2005-01432, author = {Hany Abdulsamad and Jan Peters}, title = {Hierarchical Decomposition of Nonlinear Dynamics and Control for System Identification and Policy Distillation}, journal = {CoRR}, volume = {abs/2005.01432}, year = {2020}, url = {https://arxiv.org/abs/2005.01432}, eprinttype = {arXiv}, eprint = {2005.01432}, timestamp = {Fri, 08 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2005-01432.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-05123, author = {Nikolaos Gkanatsios and Georgia Chalvatzaki and Petros Maragos and Jan Peters}, title = {Orientation Attentive Robot Grasp Synthesis}, journal = {CoRR}, volume = {abs/2006.05123}, year = {2020}, url = {https://arxiv.org/abs/2006.05123}, eprinttype = {arXiv}, eprint = {2006.05123}, timestamp = {Mon, 15 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-05123.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-05911, author = {Riad Akrour and Davide Tateo and Jan Peters}, title = {Reinforcement Learning from a Mixture of Interpretable Experts}, journal = {CoRR}, volume = {abs/2006.05911}, year = {2020}, url = {https://arxiv.org/abs/2006.05911}, eprinttype = {arXiv}, eprint = {2006.05911}, timestamp = {Sat, 13 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-05911.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-05935, author = {Dieter B{\"{u}}chler and Simon Guist and Roberto Calandra and Vincent Berenz and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning to Play Table Tennis From Scratch using Muscular Robots}, journal = {CoRR}, volume = {abs/2006.05935}, year = {2020}, url = {https://arxiv.org/abs/2006.05935}, eprinttype = {arXiv}, eprint = {2006.05935}, timestamp = {Sat, 13 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-05935.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2006-08973, author = {Andreas Look and Chen Qiu and Maja Rudolph and Jan Peters and Melih Kandemir}, title = {Deterministic Inference of Neural Stochastic Differential Equations}, journal = {CoRR}, volume = {abs/2006.08973}, year = {2020}, url = {https://arxiv.org/abs/2006.08973}, eprinttype = {arXiv}, eprint = {2006.08973}, timestamp = {Tue, 18 Jan 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2006-08973.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2007-00391, author = {Tuan Dam and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Convex Regularization in Monte-Carlo Tree Search}, journal = {CoRR}, volume = {abs/2007.00391}, year = {2020}, url = {https://arxiv.org/abs/2007.00391}, eprinttype = {arXiv}, eprint = {2007.00391}, timestamp = {Mon, 06 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2007-00391.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2007-02084, author = {Mikko Lauri and Joni Pajarinen and Jan Peters and Simone Frintrop}, title = {Multi-Sensor Next-Best-View Planning as Matroid-Constrained Submodular Maximization}, journal = {CoRR}, volume = {abs/2007.02084}, year = {2020}, url = {https://arxiv.org/abs/2007.02084}, eprinttype = {arXiv}, eprint = {2007.02084}, timestamp = {Fri, 17 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2007-02084.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-04589, author = {Leon Keller and Daniel Tanneberg and Svenja Stark and Jan Peters}, title = {Model-Based Quality-Diversity Search for Efficient Robot Learning}, journal = {CoRR}, volume = {abs/2008.04589}, year = {2020}, url = {https://arxiv.org/abs/2008.04589}, eprinttype = {arXiv}, eprint = {2008.04589}, timestamp = {Fri, 14 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-04589.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-05251, author = {Marco Ewerton and Oleg Arenz and Jan Peters}, title = {Assisted Teleoperation in Changing Environments with a Mixture of Virtual Guides}, journal = {CoRR}, volume = {abs/2008.05251}, year = {2020}, url = {https://arxiv.org/abs/2008.05251}, eprinttype = {arXiv}, eprint = {2008.05251}, timestamp = {Sun, 16 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-05251.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2008-11695, author = {Vignesh Prasad and Ruth Stock{-}Homburg and Jan Peters}, title = {Advances in Human-Robot Handshaking}, journal = {CoRR}, volume = {abs/2008.11695}, year = {2020}, url = {https://arxiv.org/abs/2008.11695}, eprinttype = {arXiv}, eprint = {2008.11695}, timestamp = {Tue, 15 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2008-11695.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-00262, author = {Joe Watson and Abraham Imohiosen and Jan Peters}, title = {Active Inference or Control as Inference? {A} Unifying View}, journal = {CoRR}, volume = {abs/2010.00262}, year = {2020}, url = {https://arxiv.org/abs/2010.00262}, eprinttype = {arXiv}, eprint = {2010.00262}, timestamp = {Mon, 12 Oct 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-00262.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-07078, author = {Andreas Look and Simona Doneva and Melih Kandemir and Rainer Gemulla and Jan Peters}, title = {Differentiable Implicit Layers}, journal = {CoRR}, volume = {abs/2010.07078}, year = {2020}, url = {https://arxiv.org/abs/2010.07078}, eprinttype = {arXiv}, eprint = {2010.07078}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-07078.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-09802, author = {Michael Lutter and Johannes Silberbauer and Joe Watson and Jan Peters}, title = {A Differentiable Newton Euler Algorithm for Multi-body Model Learning}, journal = {CoRR}, volume = {abs/2010.09802}, year = {2020}, url = {https://arxiv.org/abs/2010.09802}, eprinttype = {arXiv}, eprint = {2010.09802}, timestamp = {Mon, 26 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-09802.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-13129, author = {Julen Urain and Michele Ginesi and Davide Tateo and Jan Peters}, title = {ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flows}, journal = {CoRR}, volume = {abs/2010.13129}, year = {2020}, url = {https://arxiv.org/abs/2010.13129}, eprinttype = {arXiv}, eprint = {2010.13129}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-13129.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-13483, author = {Kai Ploeger and Michael Lutter and Jan Peters}, title = {High Acceleration Reinforcement Learning for Real-World Juggling with Binary Rewards}, journal = {CoRR}, volume = {abs/2010.13483}, year = {2020}, url = {https://arxiv.org/abs/2010.13483}, eprinttype = {arXiv}, eprint = {2010.13483}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-13483.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-13766, author = {Samuele Tosatto and Georgia Chalvatzaki and Jan Peters}, title = {Contextual Latent-Movements Off-Policy Optimization for Robotic Manipulation Skills}, journal = {CoRR}, volume = {abs/2010.13766}, year = {2020}, url = {https://arxiv.org/abs/2010.13766}, eprinttype = {arXiv}, eprint = {2010.13766}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-13766.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2010-14771, author = {Samuele Tosatto and Jo{\~{a}}o Carvalho and Jan Peters}, title = {Batch Reinforcement Learning with a Nonparametric Off-Policy Policy Gradient}, journal = {CoRR}, volume = {abs/2010.14771}, year = {2020}, url = {https://arxiv.org/abs/2010.14771}, eprinttype = {arXiv}, eprint = {2010.14771}, timestamp = {Mon, 02 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2010-14771.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-01734, author = {Michael Lutter and Johannes Silberbauer and Joe Watson and Jan Peters}, title = {Differentiable Physics Models for Real-world Offline Model-based Reinforcement Learning}, journal = {CoRR}, volume = {abs/2011.01734}, year = {2020}, url = {https://arxiv.org/abs/2011.01734}, eprinttype = {arXiv}, eprint = {2011.01734}, timestamp = {Fri, 06 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-01734.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-05217, author = {Hany Abdulsamad and Peter Nickl and Pascal Klink and Jan Peters}, title = {A Variational Infinite Mixture for Probabilistic Inverse Dynamics Learning}, journal = {CoRR}, volume = {abs/2011.05217}, year = {2020}, url = {https://arxiv.org/abs/2011.05217}, eprinttype = {arXiv}, eprint = {2011.05217}, timestamp = {Thu, 12 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-05217.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2011-07016, author = {Riad Akrour and Asma Atamna and Jan Peters}, title = {Convex Optimization with an Interpolation-based Projection and its Application to Deep Learning}, journal = {CoRR}, volume = {abs/2011.07016}, year = {2020}, url = {https://arxiv.org/abs/2011.07016}, eprinttype = {arXiv}, eprint = {2011.07016}, timestamp = {Wed, 18 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2011-07016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-03806, author = {Sebastian H{\"{o}}fer and Kostas E. Bekris and Ankur Handa and Juan Camilo Gamboa Higuera and Florian Golemo and Melissa Mozifian and Christopher G. Atkeson and Dieter Fox and Ken Goldberg and John Leonard and C. Karen Liu and Jan Peters and Shuran Song and Peter Welinder and Martha White}, title = {Perspectives on Sim2Real Transfer for Robotics: {A} Summary of the {R:} {SS} 2020 Workshop}, journal = {CoRR}, volume = {abs/2012.03806}, year = {2020}, url = {https://arxiv.org/abs/2012.03806}, eprinttype = {arXiv}, eprint = {2012.03806}, timestamp = {Tue, 29 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-03806.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-2012-06224, author = {Julen Urain and Davide Tateo and Tianyu Ren and Jan Peters}, title = {Structured Policy Representation: Imposing Stability in arbitrarily conditioned dynamic systems}, journal = {CoRR}, volume = {abs/2012.06224}, year = {2020}, url = {https://arxiv.org/abs/2012.06224}, eprinttype = {arXiv}, eprint = {2012.06224}, timestamp = {Sat, 02 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-2012-06224.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/entropy/BelousovP19, author = {Boris Belousov and Jan Peters}, title = {Entropic Regularization of Markov Decision Processes}, journal = {Entropy}, volume = {21}, number = {7}, pages = {674}, year = {2019}, url = {https://doi.org/10.3390/e21070674}, doi = {10.3390/E21070674}, timestamp = {Fri, 25 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/entropy/BelousovP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/SchurmannMPB19, author = {Tim Sch{\"{u}}rmann and Betty J. Mohler and Jan Peters and Philipp Beckerle}, title = {How Cognitive Models of Human Body Experience Might Push Robotics}, journal = {Frontiers Neurorobotics}, volume = {13}, pages = {14}, year = {2019}, url = {https://doi.org/10.3389/fnbot.2019.00014}, doi = {10.3389/FNBOT.2019.00014}, timestamp = {Tue, 09 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/finr/SchurmannMPB19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/EwertonAMKKTP19, author = {Marco Ewerton and Oleg Arenz and Guilherme Maeda and Dorothea Koert and Zlatko Kolev and Masaki Takahashi and Jan Peters}, title = {Learning Trajectory Distributions for Assisted Teleoperation and Path Planning}, journal = {Frontiers Robotics {AI}}, volume = {6}, pages = {89}, year = {2019}, url = {https://doi.org/10.3389/frobt.2019.00089}, doi = {10.3389/FROBT.2019.00089}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/firai/EwertonAMKKTP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/CeleminMRPK19, author = {Carlos Celemin and Guilherme Maeda and Javier Ruiz{-}del{-}Solar and Jan Peters and Jens Kober}, title = {Reinforcement learning of motor skills using Policy Search and human corrective advice}, journal = {Int. J. Robotics Res.}, volume = {38}, number = {14}, year = {2019}, url = {https://doi.org/10.1177/0278364919871998}, doi = {10.1177/0278364919871998}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/CeleminMRPK19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/PajarinenTAPN19, author = {Joni Pajarinen and Hong Linh Thai and Riad Akrour and Jan Peters and Gerhard Neumann}, title = {Compatible natural gradient policy search}, journal = {Mach. Learn.}, volume = {108}, number = {8-9}, pages = {1443--1466}, year = {2019}, url = {https://doi.org/10.1007/s10994-019-05807-0}, doi = {10.1007/S10994-019-05807-0}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/PajarinenTAPN19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/ParisiTPK19, author = {Simone Parisi and Voot Tangkaratt and Jan Peters and Mohammad Emtiyaz Khan}, title = {TD-regularized actor-critic methods}, journal = {Mach. Learn.}, volume = {108}, number = {8-9}, pages = {1467--1501}, year = {2019}, url = {https://doi.org/10.1007/s10994-019-05788-0}, doi = {10.1007/S10994-019-05788-0}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/ParisiTPK19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/TannebergPR19, author = {Daniel Tanneberg and Jan Peters and Elmar Rueckert}, title = {Intrinsic motivation and mental replay enable efficient online adaptation in stochastic recurrent networks}, journal = {Neural Networks}, volume = {109}, pages = {67--80}, year = {2019}, url = {https://doi.org/10.1016/j.neunet.2018.10.005}, doi = {10.1016/J.NEUNET.2018.10.005}, timestamp = {Sat, 30 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/nn/TannebergPR19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/Koc019, author = {Okan Koc and Jan Peters}, title = {Learning to Serve: An Experimental Study for a New Learning From Demonstrations Framework}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {4}, number = {2}, pages = {1784--1791}, year = {2019}, url = {https://doi.org/10.1109/LRA.2019.2896466}, doi = {10.1109/LRA.2019.2896466}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/Koc019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/Brandherm0NA19, author = {Florian Brandherm and Jan Peters and Gerhard Neumann and Riad Akrour}, title = {Learning Replanning Policies With Direct Policy Search}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {4}, number = {2}, pages = {2196--2203}, year = {2019}, url = {https://doi.org/10.1109/LRA.2019.2901656}, doi = {10.1109/LRA.2019.2901656}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/Brandherm0NA19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/KoertPSTRP19, author = {Dorothea Koert and Joni Pajarinen and Albert Schotschneider and Susanne Trick and Constantin A. Rothkopf and Jan Peters}, title = {Learning Intention Aware Online Adaptation of Movement Primitives}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {4}, number = {4}, pages = {3719--3726}, year = {2019}, url = {https://doi.org/10.1109/LRA.2019.2928760}, doi = {10.1109/LRA.2019.2928760}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/KoertPSTRP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/robotics/Gomez-GonzalezN19, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Yassine Nemmour and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Reliable Real-Time Ball Tracking for Robot Table Tennis}, journal = {Robotics}, volume = {8}, number = {4}, pages = {90}, year = {2019}, url = {https://doi.org/10.3390/robotics8040090}, doi = {10.3390/ROBOTICS8040090}, timestamp = {Fri, 07 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/robotics/Gomez-GonzalezN19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/KocMP19, author = {Okan Koc and Guilherme Maeda and Jan Peters}, title = {Optimizing the Execution of Dynamic Robot Movements With Learning Control}, journal = {{IEEE} Trans. Robotics}, volume = {35}, number = {4}, pages = {909--924}, year = {2019}, url = {https://doi.org/10.1109/TRO.2019.2906558}, doi = {10.1109/TRO.2019.2906558}, timestamp = {Wed, 21 Aug 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/trob/KocMP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/atal/LauriP019, author = {Mikko Lauri and Joni Pajarinen and Jan Peters}, editor = {Edith Elkind and Manuela Veloso and Noa Agmon and Matthew E. Taylor}, title = {Information Gathering in Decentralized POMDPs by Policy Graph Improvement}, booktitle = {Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, {AAMAS} '19, Montreal, QC, Canada, May 13-17, 2019}, pages = {1143--1151}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, year = {2019}, url = {http://dl.acm.org/citation.cfm?id=3331815}, timestamp = {Wed, 29 May 2019 16:36:58 +0200}, biburl = {https://dblp.org/rec/conf/atal/LauriP019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/KlinkAB019, author = {Pascal Klink and Hany Abdulsamad and Boris Belousov and Jan Peters}, editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura}, title = {Self-Paced Contextual Reinforcement Learning}, booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {100}, pages = {513--529}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v100/klink20a.html}, timestamp = {Mon, 25 May 2020 12:12:52 +0200}, biburl = {https://dblp.org/rec/conf/corl/KlinkAB019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/LutterBLC019, author = {Michael Lutter and Boris Belousov and Kim Listmann and Debora Clever and Jan Peters}, editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura}, title = {{HJB} Optimal Feedback Control with Deep Differential Value Functions and Action Constraints}, booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {100}, pages = {640--650}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v100/lutter20a.html}, timestamp = {Mon, 25 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/corl/LutterBLC019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/WatsonA019, author = {Joe Watson and Hany Abdulsamad and Jan Peters}, editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura}, title = {Stochastic Optimal Control as Approximate Input Inference}, booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {100}, pages = {697--716}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v100/watson20a.html}, timestamp = {Mon, 25 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/corl/WatsonA019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/SchultheisBA019, author = {Matthias Schultheis and Boris Belousov and Hany Abdulsamad and Jan Peters}, editor = {Leslie Pack Kaelbling and Danica Kragic and Komei Sugiura}, title = {Receding Horizon Curiosity}, booktitle = {3rd Annual Conference on Robot Learning, CoRL 2019, Osaka, Japan, October 30 - November 1, 2019, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {100}, pages = {1278--1288}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v100/schultheis20a.html}, timestamp = {Mon, 25 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/corl/SchultheisBA019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/BelousovSWVT019, author = {Boris Belousov and Alymbek Sadybakasov and Bastian Wibranek and Filipe Veiga and Oliver Tessmann and Jan Peters}, title = {Building a Library of Tactile Skills Based on FingerVision}, booktitle = {19th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2019, Toronto, ON, Canada, October 15-17, 2019}, pages = {717--722}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/Humanoids43949.2019.9035000}, doi = {10.1109/HUMANOIDS43949.2019.9035000}, timestamp = {Sun, 02 Oct 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/BelousovSWVT019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iclr/LutterRP19, author = {Michael Lutter and Christian Ritter and Jan Peters}, title = {Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning}, booktitle = {7th International Conference on Learning Representations, {ICLR} 2019, New Orleans, LA, USA, May 6-9, 2019}, publisher = {OpenReview.net}, year = {2019}, url = {https://openreview.net/forum?id=BklHpjCqKm}, timestamp = {Thu, 25 Jul 2019 13:03:15 +0200}, biburl = {https://dblp.org/rec/conf/iclr/LutterRP19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AkrourP0N19, author = {Riad Akrour and Joni Pajarinen and Jan Peters and Gerhard Neumann}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, title = {Projections for Approximate Policy Iteration Algorithms}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {97}, pages = {181--190}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v97/akrour19a.html}, timestamp = {Tue, 11 Jun 2019 15:37:38 +0200}, biburl = {https://dblp.org/rec/conf/icml/AkrourP0N19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/Becker-Ehmck0S19, author = {Philip Becker{-}Ehmck and Jan Peters and Patrick van der Smagt}, editor = {Kamalika Chaudhuri and Ruslan Salakhutdinov}, title = {Switching Linear Dynamics for Variational Bayes Filtering}, booktitle = {Proceedings of the 36th International Conference on Machine Learning, {ICML} 2019, 9-15 June 2019, Long Beach, California, {USA}}, series = {Proceedings of Machine Learning Research}, volume = {97}, pages = {553--562}, publisher = {{PMLR}}, year = {2019}, url = {http://proceedings.mlr.press/v97/becker-ehmck19a.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icml/Becker-Ehmck0S19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/TosattoDPR019, author = {Samuele Tosatto and Carlo D'Eramo and Joni Pajarinen and Marcello Restelli and Jan Peters}, title = {Exploration Driven by an Optimistic Bellman Equation}, booktitle = {International Joint Conference on Neural Networks, {IJCNN} 2019 Budapest, Hungary, July 14-19, 2019}, pages = {1--8}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IJCNN.2019.8851736}, doi = {10.1109/IJCNN.2019.8851736}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/TosattoDPR019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/NassB019, author = {David Nass and Boris Belousov and Jan Peters}, title = {Entropic Risk Measure in Policy Search}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {1101--1106}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8967699}, doi = {10.1109/IROS40897.2019.8967699}, timestamp = {Fri, 31 Jan 2020 10:27:14 +0100}, biburl = {https://dblp.org/rec/conf/iros/NassB019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Stark0R19, author = {Svenja Stark and Jan Peters and Elmar Rueckert}, title = {Experience Reuse with Probabilistic Movement Primitives}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {1210--1217}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8968545}, doi = {10.1109/IROS40897.2019.8968545}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/Stark0R19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Urain019, author = {Julen Urain and Jan Peters}, title = {Generalized Multiple Correlation Coefficient as a Similarity Measurement between Trajectories}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {1363--1369}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8967884}, doi = {10.1109/IROS40897.2019.8967884}, timestamp = {Fri, 31 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/Urain019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/EwertonMKKT019, author = {Marco Ewerton and Guilherme Maeda and Dorothea Koert and Zlatko Kolev and Masaki Takahashi and Jan Peters}, title = {Reinforcement Learning of Trajectory Distributions: Applications in Assisted Teleoperation and Motion Planning}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {4294--4300}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8967856}, doi = {10.1109/IROS40897.2019.8967856}, timestamp = {Fri, 31 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/EwertonMKKT019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LiuHIS0H19, author = {Zinan Liu and Arne Hitzmann and Shuhei Ikemoto and Svenja Stark and Jan Peters and Koh Hosoda}, title = {Local Online Motor Babbling: Learning Motor Abundance of a Musculoskeletal Robot Arm\({}^{\mbox{*}}\)}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {6594--6601}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8967791}, doi = {10.1109/IROS40897.2019.8967791}, timestamp = {Fri, 31 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LiuHIS0H19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/CelikA019, author = {Onur Celik and Hany Abdulsamad and Jan Peters}, title = {Chance-Constrained Trajectory Optimization for Non-linear Systems with Unknown Stochastic Dynamics}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {6828--6833}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8967794}, doi = {10.1109/IROS40897.2019.8967794}, timestamp = {Fri, 31 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/CelikA019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/TrickK0R19, author = {Susanne Trick and Dorothea Koert and Jan Peters and Constantin A. Rothkopf}, title = {Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {7009--7016}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8968171}, doi = {10.1109/IROS40897.2019.8968171}, timestamp = {Tue, 29 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/TrickK0R19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LutterL019, author = {Michael Lutter and Kim Listmann and Jan Peters}, title = {Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems}, booktitle = {2019 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2019, Macau, SAR, China, November 3-8, 2019}, pages = {7718--7725}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/IROS40897.2019.8968268}, doi = {10.1109/IROS40897.2019.8968268}, timestamp = {Fri, 31 Jan 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/LutterL019.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/smc/OzdenizciMW0SCG19, author = {Ozan {\"{O}}zdenizci and Timm Meyer and Felix A. Wichmann and Jan Peters and Bernhard Sch{\"{o}}lkopf and M{\"{u}}jdat {\c{C}}etin and Moritz Grosse{-}Wentrup}, title = {Neural Signatures of Motor Skill in the Resting Brain}, booktitle = {2019 {IEEE} International Conference on Systems, Man and Cybernetics, {SMC} 2019, Bari, Italy, October 6-9, 2019}, pages = {4387--4394}, publisher = {{IEEE}}, year = {2019}, url = {https://doi.org/10.1109/SMC.2019.8914252}, doi = {10.1109/SMC.2019.8914252}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/smc/OzdenizciMW0SCG19.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-01240, author = {Paavo Parmas and Carl Edward Rasmussen and Jan Peters and Kenji Doya}, title = {{PIPPS:} Flexible Model-Based Policy Search Robust to the Curse of Chaos}, journal = {CoRR}, volume = {abs/1902.01240}, year = {2019}, url = {http://arxiv.org/abs/1902.01240}, eprinttype = {arXiv}, eprint = {1902.01240}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-01240.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-02823, author = {Joni Pajarinen and Hong Linh Thai and Riad Akrour and Jan Peters and Gerhard Neumann}, title = {Compatible Natural Gradient Policy Search}, journal = {CoRR}, volume = {abs/1902.02823}, year = {2019}, url = {http://arxiv.org/abs/1902.02823}, eprinttype = {arXiv}, eprint = {1902.02823}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-02823.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-04524, author = {Diego Agudelo{-}Espa{\~{n}}a and Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Stefan Bauer and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Bayesian Online Detection and Prediction of Change Points}, journal = {CoRR}, volume = {abs/1902.04524}, year = {2019}, url = {http://arxiv.org/abs/1902.04524}, eprinttype = {arXiv}, eprint = {1902.04524}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-04524.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-05605, author = {Aditya Bhatt and Daniel Palenicek and Boris Belousov and Max Argus and Artemij Amiranashvili and Thomas Brox and Jan Peters}, title = {CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity}, journal = {CoRR}, volume = {abs/1902.05605}, year = {2019}, url = {http://arxiv.org/abs/1902.05605}, eprinttype = {arXiv}, eprint = {1902.05605}, timestamp = {Thu, 09 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-05605.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1902-09840, author = {Mikko Lauri and Joni Pajarinen and Jan Peters}, title = {Information Gathering in Decentralized POMDPs by Policy Graph Improvement}, journal = {CoRR}, volume = {abs/1902.09840}, year = {2019}, url = {http://arxiv.org/abs/1902.09840}, eprinttype = {arXiv}, eprint = {1902.09840}, timestamp = {Tue, 21 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1902-09840.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1903-09516, author = {Kristian Kersting and Jan Peters and Constantin A. Rothkopf}, title = {Was ist eine Professur fuer Kuenstliche Intelligenz?}, journal = {CoRR}, volume = {abs/1903.09516}, year = {2019}, url = {http://arxiv.org/abs/1903.09516}, eprinttype = {arXiv}, eprint = {1903.09516}, timestamp = {Mon, 01 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1903-09516.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-03665, author = {Dieter B{\"{u}}chler and Roberto Calandra and Jan Peters}, title = {Learning to Control Highly Accelerated Ballistic Movements on Muscular Robots}, journal = {CoRR}, volume = {abs/1904.03665}, year = {2019}, url = {http://arxiv.org/abs/1904.03665}, eprinttype = {arXiv}, eprint = {1904.03665}, timestamp = {Thu, 25 Apr 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-03665.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1904-12336, author = {Zinan Liu and Kai Ploeger and Svenja Stark and Elmar Rueckert and Jan Peters}, title = {Learning walk and trot from the same objective using different types of exploration}, journal = {CoRR}, volume = {abs/1904.12336}, year = {2019}, url = {http://arxiv.org/abs/1904.12336}, eprinttype = {arXiv}, eprint = {1904.12336}, timestamp = {Thu, 02 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1904-12336.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1905-12434, author = {Philip Becker{-}Ehmck and Jan Peters and Patrick van der Smagt}, title = {Switching Linear Dynamics for Variational Bayes Filtering}, journal = {CoRR}, volume = {abs/1905.12434}, year = {2019}, url = {http://arxiv.org/abs/1905.12434}, eprinttype = {arXiv}, eprint = {1905.12434}, timestamp = {Mon, 03 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1905-12434.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-09013, author = {Zinan Liu and Arne Hitzmann and Shuhei Ikemoto and Svenja Stark and Jan Peters and Koh Hosoda}, title = {Local Online Motor Babbling: Learning Motor Abundance of {A} Musculoskeletal Robot Arm}, journal = {CoRR}, volume = {abs/1906.09013}, year = {2019}, url = {http://arxiv.org/abs/1906.09013}, eprinttype = {arXiv}, eprint = {1906.09013}, timestamp = {Mon, 04 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-09013.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-09090, author = {David Nass and Boris Belousov and Jan Peters}, title = {Entropic Risk Measure in Policy Search}, journal = {CoRR}, volume = {abs/1906.09090}, year = {2019}, url = {http://arxiv.org/abs/1906.09090}, eprinttype = {arXiv}, eprint = {1906.09090}, timestamp = {Mon, 24 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-09090.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-09802, author = {Julen Urain and Jan Peters}, title = {Generalized Multiple Correlation Coefficient as a Similarity Measurement between Trajectories}, journal = {CoRR}, volume = {abs/1906.09802}, year = {2019}, url = {http://arxiv.org/abs/1906.09802}, eprinttype = {arXiv}, eprint = {1906.09802}, timestamp = {Mon, 08 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-09802.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1906-11003, author = {Onur Celik and Hany Abdulsamad and Jan Peters}, title = {Chance-Constrained Trajectory Optimization for Non-linear Systems with Unknown Stochastic Dynamics}, journal = {CoRR}, volume = {abs/1906.11003}, year = {2019}, url = {http://arxiv.org/abs/1906.11003}, eprinttype = {arXiv}, eprint = {1906.11003}, timestamp = {Thu, 27 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1906-11003.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1907-02426, author = {Susanne Trick and Dorothea Koert and Jan Peters and Constantin A. Rothkopf}, title = {Multimodal Uncertainty Reduction for Intention Recognition in Human-Robot Interaction}, journal = {CoRR}, volume = {abs/1907.02426}, year = {2019}, url = {http://arxiv.org/abs/1907.02426}, eprinttype = {arXiv}, eprint = {1907.02426}, timestamp = {Mon, 08 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-02426.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1907-04214, author = {Boris Belousov and Jan Peters}, title = {Entropic Regularization of Markov Decision Processes}, journal = {CoRR}, volume = {abs/1907.04214}, year = {2019}, url = {http://arxiv.org/abs/1907.04214}, eprinttype = {arXiv}, eprint = {1907.04214}, timestamp = {Wed, 17 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-04214.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1907-04489, author = {Michael Lutter and Kim Listmann and Jan Peters}, title = {Deep Lagrangian Networks for end-to-end learning of energy-based control for under-actuated systems}, journal = {CoRR}, volume = {abs/1907.04489}, year = {2019}, url = {http://arxiv.org/abs/1907.04489}, eprinttype = {arXiv}, eprint = {1907.04489}, timestamp = {Wed, 17 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-04489.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1907-04490, author = {Michael Lutter and Christian Ritter and Jan Peters}, title = {Deep Lagrangian Networks: Using Physics as Model Prior for Deep Learning}, journal = {CoRR}, volume = {abs/1907.04490}, year = {2019}, url = {http://arxiv.org/abs/1907.04490}, eprinttype = {arXiv}, eprint = {1907.04490}, timestamp = {Wed, 17 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-04490.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1907-04685, author = {Fabio Muratore and Michael Gienger and Jan Peters}, title = {Assessing Transferability from Simulation to Reality for Reinforcement Learning}, journal = {CoRR}, volume = {abs/1907.04685}, year = {2019}, url = {http://arxiv.org/abs/1907.04685}, eprinttype = {arXiv}, eprint = {1907.04685}, timestamp = {Wed, 17 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1907-04685.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1908-03936, author = {Svenja Stark and Jan Peters and Elmar Rueckert}, title = {Experience Reuse with Probabilistic Movement Primitives}, journal = {CoRR}, volume = {abs/1908.03936}, year = {2019}, url = {http://arxiv.org/abs/1908.03936}, eprinttype = {arXiv}, eprint = {1908.03936}, timestamp = {Mon, 19 Aug 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1908-03936.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1908-06012, author = {Zhang{-}Wei Hong and Joni Pajarinen and Jan Peters}, title = {Model-based Lookahead Reinforcement Learning}, journal = {CoRR}, volume = {abs/1908.06012}, year = {2019}, url = {http://arxiv.org/abs/1908.06012}, eprinttype = {arXiv}, eprint = {1908.06012}, timestamp = {Mon, 19 Aug 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1908-06012.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1908-07332, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Yassine Nemmour and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Reliable Real Time Ball Tracking for Robot Table Tennis}, journal = {CoRR}, volume = {abs/1908.07332}, year = {2019}, url = {http://arxiv.org/abs/1908.07332}, eprinttype = {arXiv}, eprint = {1908.07332}, timestamp = {Mon, 26 Aug 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1908-07332.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1909-03895, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Sergey Prokudin and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Real Time Trajectory Prediction Using Deep Conditional Generative Models}, journal = {CoRR}, volume = {abs/1909.03895}, year = {2019}, url = {http://arxiv.org/abs/1909.03895}, eprinttype = {arXiv}, eprint = {1909.03895}, timestamp = {Wed, 18 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-03895.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1909-06153, author = {Michael Lutter and Boris Belousov and Kim Listmann and Debora Clever and Jan Peters}, title = {{HJB} Optimal Feedback Control with Deep Differential Value Functions and Action Constraints}, journal = {CoRR}, volume = {abs/1909.06153}, year = {2019}, url = {http://arxiv.org/abs/1909.06153}, eprinttype = {arXiv}, eprint = {1909.06153}, timestamp = {Wed, 18 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-06153.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1909-09669, author = {Boris Belousov and Alymbek Sadybakasov and Bastian Wibranek and Filipe Veiga and Oliver Tessmann and Jan Peters}, title = {Building a Library of Tactile Skills Based on FingerVision}, journal = {CoRR}, volume = {abs/1909.09669}, year = {2019}, url = {http://arxiv.org/abs/1909.09669}, eprinttype = {arXiv}, eprint = {1909.09669}, timestamp = {Fri, 27 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1909-09669.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1910-02826, author = {Pascal Klink and Hany Abdulsamad and Boris Belousov and Jan Peters}, title = {Self-Paced Contextual Reinforcement Learning}, journal = {CoRR}, volume = {abs/1910.02826}, year = {2019}, url = {http://arxiv.org/abs/1910.02826}, eprinttype = {arXiv}, eprint = {1910.02826}, timestamp = {Wed, 09 Oct 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-02826.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1910-03003, author = {Joe Watson and Hany Abdulsamad and Jan Peters}, title = {Stochastic Optimal Control as Approximate Input Inference}, journal = {CoRR}, volume = {abs/1910.03003}, year = {2019}, url = {http://arxiv.org/abs/1910.03003}, eprinttype = {arXiv}, eprint = {1910.03003}, timestamp = {Wed, 09 Oct 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-03003.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1910-03620, author = {Matthias Schultheis and Boris Belousov and Hany Abdulsamad and Jan Peters}, title = {Receding Horizon Curiosity}, journal = {CoRR}, volume = {abs/1910.03620}, year = {2019}, url = {http://arxiv.org/abs/1910.03620}, eprinttype = {arXiv}, eprint = {1910.03620}, timestamp = {Wed, 16 Oct 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1910-03620.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-00384, author = {Tuan Dam and Pascal Klink and Carlo D'Eramo and Jan Peters and Joni Pajarinen}, title = {Generalized Mean Estimation in Monte-Carlo Tree Search}, journal = {CoRR}, volume = {abs/1911.00384}, year = {2019}, url = {http://arxiv.org/abs/1911.00384}, eprinttype = {arXiv}, eprint = {1911.00384}, timestamp = {Mon, 11 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-00384.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1911-00926, author = {Daniel Tanneberg and Elmar Rueckert and Jan Peters}, title = {Learning Algorithmic Solutions to Symbolic Planning Tasks with a Neural Computer}, journal = {CoRR}, volume = {abs/1911.00926}, year = {2019}, url = {http://arxiv.org/abs/1911.00926}, eprinttype = {arXiv}, eprint = {1911.00926}, timestamp = {Mon, 11 Nov 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1911-00926.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ar/ParaschosR0N18, author = {Alexandros Paraschos and Elmar Rueckert and Jan Peters and Gerhard Neumann}, title = {Probabilistic movement primitives under unknown system dynamics}, journal = {Adv. Robotics}, volume = {32}, number = {6}, pages = {297--310}, year = {2018}, url = {https://doi.org/10.1080/01691864.2018.1437674}, doi = {10.1080/01691864.2018.1437674}, timestamp = {Sat, 25 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ar/ParaschosR0N18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ar/OsaPN18, author = {Takayuki Osa and Jan Peters and Gerhard Neumann}, title = {Hierarchical reinforcement learning of multiple grasping strategies with human instructions}, journal = {Adv. Robotics}, volume = {32}, number = {18}, pages = {955--968}, year = {2018}, url = {https://doi.org/10.1080/01691864.2018.1509018}, doi = {10.1080/01691864.2018.1509018}, timestamp = {Sat, 25 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ar/OsaPN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/ParaschosDPN18, author = {Alexandros Paraschos and Christian Daniel and Jan Peters and Gerhard Neumann}, title = {Using probabilistic movement primitives in robotics}, journal = {Auton. Robots}, volume = {42}, number = {3}, pages = {529--551}, year = {2018}, url = {https://doi.org/10.1007/s10514-017-9648-7}, doi = {10.1007/S10514-017-9648-7}, timestamp = {Fri, 30 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/arobots/ParaschosDPN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/KroemerLLP18, author = {Oliver Kroemer and Simon Leischnig and Stefan Luettgen and Jan Peters}, title = {A kernel-based approach to learning contact distributions for robot manipulation tasks}, journal = {Auton. Robots}, volume = {42}, number = {3}, pages = {581--600}, year = {2018}, url = {https://doi.org/10.1007/s10514-017-9651-z}, doi = {10.1007/S10514-017-9651-Z}, timestamp = {Tue, 06 Mar 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/arobots/KroemerLLP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/finr/EwertonRWKWPM18, author = {Marco Ewerton and David Rother and Jakob Weimar and Gerrit Kollegger and Josef Wiemeyer and Jan Peters and Guilherme Maeda}, title = {Assisting Movement Training and Execution With Visual and Haptic Feedback}, journal = {Frontiers Neurorobotics}, volume = {12}, pages = {24}, year = {2018}, url = {https://doi.org/10.3389/fnbot.2018.00024}, doi = {10.3389/FNBOT.2018.00024}, timestamp = {Tue, 09 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/finr/EwertonRWKWPM18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ftrob/OsaPNBA018, author = {Takayuki Osa and Joni Pajarinen and Gerhard Neumann and J. Andrew Bagnell and Pieter Abbeel and Jan Peters}, title = {An Algorithmic Perspective on Imitation Learning}, journal = {Found. Trends Robotics}, volume = {7}, number = {1-2}, pages = {1--179}, year = {2018}, url = {https://doi.org/10.1561/2300000053}, doi = {10.1561/2300000053}, timestamp = {Thu, 10 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ftrob/OsaPNBA018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/AkrourAAPN18, author = {Riad Akrour and Abbas Abdolmaleki and Hany Abdulsamad and Jan Peters and Gerhard Neumann}, title = {Model-Free Trajectory-based Policy Optimization with Monotonic Improvement}, journal = {J. Mach. Learn. Res.}, volume = {19}, pages = {14:1--14:25}, year = {2018}, url = {http://jmlr.org/papers/v19/17-329.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/AkrourAAPN18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/SosicRPZK18, author = {Adrian Sosic and Elmar Rueckert and Jan Peters and Abdelhak M. Zoubir and Heinz Koeppl}, title = {Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling}, journal = {J. Mach. Learn. Res.}, volume = {19}, pages = {69:1--69:45}, year = {2018}, url = {http://jmlr.org/papers/v19/18-113.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/SosicRPZK18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/ManschitzGKP18, author = {Simon Manschitz and Michael Gienger and Jens Kober and Jan Peters}, title = {Mixture of Attractors: {A} Novel Movement Primitive Representation for Learning Motor Skills From Demonstrations}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {3}, number = {2}, pages = {926--933}, year = {2018}, url = {https://doi.org/10.1109/LRA.2018.2792531}, doi = {10.1109/LRA.2018.2792531}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/ManschitzGKP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/VinogradskaBP18, author = {Julia Vinogradska and Bastian Bischoff and Jan Peters}, title = {Approximate Value Iteration Based on Numerical Quadrature}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {3}, number = {2}, pages = {1330--1337}, year = {2018}, url = {https://doi.org/10.1109/LRA.2018.2798279}, doi = {10.1109/LRA.2018.2798279}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/VinogradskaBP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/BuchlerCSP18, author = {Dieter Buchler and Roberto Calandra and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Control of Musculoskeletal Systems Using Learned Dynamics Models}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {3}, number = {4}, pages = {3161--3168}, year = {2018}, url = {https://doi.org/10.1109/LRA.2018.2849601}, doi = {10.1109/LRA.2018.2849601}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/BuchlerCSP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/KocMP18, author = {Okan Koc and Guilherme Maeda and Jan Peters}, title = {Online optimal trajectory generation for robot table tennis}, journal = {Robotics Auton. Syst.}, volume = {105}, pages = {121--137}, year = {2018}, url = {https://doi.org/10.1016/j.robot.2018.03.012}, doi = {10.1016/J.ROBOT.2018.03.012}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/KocMP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/toh/VeigaPH18, author = {Filipe Veiga and Jan Peters and Tucker Hermans}, title = {Grip Stabilization of Novel Objects Using Slip Prediction}, journal = {{IEEE} Trans. Haptics}, volume = {11}, number = {4}, pages = {531--542}, year = {2018}, url = {https://doi.org/10.1109/TOH.2018.2837744}, doi = {10.1109/TOH.2018.2837744}, timestamp = {Sat, 30 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/toh/VeigaPH18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/MuratoreTG018, author = {Fabio Muratore and Felix Treede and Michael Gienger and Jan Peters}, title = {Domain Randomization for Simulation-Based Policy Optimization with Transferability Assessment}, booktitle = {2nd Annual Conference on Robot Learning, CoRL 2018, Z{\"{u}}rich, Switzerland, 29-31 October 2018, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {87}, pages = {700--713}, publisher = {{PMLR}}, year = {2018}, url = {http://proceedings.mlr.press/v87/muratore18a.html}, timestamp = {Wed, 03 Apr 2019 18:17:24 +0200}, biburl = {https://dblp.org/rec/conf/corl/MuratoreTG018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/KoertTEL018, author = {Dorothea Koert and Susanne Trick and Marco Ewerton and Michael Lutter and Jan Peters}, title = {Online Learning of an Open-Ended Skill Library for Collaborative Tasks}, booktitle = {18th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2018, Beijing, China, November 6-9, 2018}, pages = {1--9}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/HUMANOIDS.2018.8625031}, doi = {10.1109/HUMANOIDS.2018.8625031}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/KoertTEL018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/HoelscherK0P18, author = {Janine Hoelscher and Dorothea Koert and Jan Peters and Joni Pajarinen}, title = {Utilizing Human Feedback in {POMDP} Execution and Specification}, booktitle = {18th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2018, Beijing, China, November 6-9, 2018}, pages = {104--111}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/HUMANOIDS.2018.8625022}, doi = {10.1109/HUMANOIDS.2018.8625022}, timestamp = {Fri, 25 Jan 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/HoelscherK0P18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/ParmasR0D18, author = {Paavo Parmas and Carl Edward Rasmussen and Jan Peters and Kenji Doya}, editor = {Jennifer G. Dy and Andreas Krause}, title = {{PIPPS:} Flexible Model-Based Policy Search Robust to the Curse of Chaos}, booktitle = {Proceedings of the 35th International Conference on Machine Learning, {ICML} 2018, Stockholmsm{\"{a}}ssan, Stockholm, Sweden, July 10-15, 2018}, series = {Proceedings of Machine Learning Research}, volume = {80}, pages = {4062--4071}, publisher = {{PMLR}}, year = {2018}, url = {http://proceedings.mlr.press/v80/parmas18a.html}, timestamp = {Wed, 03 Apr 2019 18:17:30 +0200}, biburl = {https://dblp.org/rec/conf/icml/ParmasR0D18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LioutikovMVK018, author = {Rudolf Lioutikov and Guilherme Maeda and Filipe Veiga and Kristian Kersting and Jan Peters}, title = {Inducing Probabilistic Context-Free Grammars for the Sequencing of Movement Primitives}, booktitle = {2018 {IEEE} International Conference on Robotics and Automation, {ICRA} 2018, Brisbane, Australia, May 21-25, 2018}, pages = {1--8}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICRA.2018.8460190}, doi = {10.1109/ICRA.2018.8460190}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/LioutikovMVK018.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/PinslerAO0N18, author = {Robert Pinsler and Riad Akrour and Takayuki Osa and Jan Peters and Gerhard Neumann}, title = {Sample and Feedback Efficient Hierarchical Reinforcement Learning from Human Preferences}, booktitle = {2018 {IEEE} International Conference on Robotics and Automation, {ICRA} 2018, Brisbane, Australia, May 21-25, 2018}, pages = {596--601}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICRA.2018.8460907}, doi = {10.1109/ICRA.2018.8460907}, timestamp = {Wed, 19 Sep 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/PinslerAO0N18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KoertMNP18, author = {Dorothea Koert and Guilherme Maeda and Gerhard Neumann and Jan Peters}, title = {Learning Coupled Forward-Inverse Models with Combined Prediction Errors}, booktitle = {2018 {IEEE} International Conference on Robotics and Automation, {ICRA} 2018, Brisbane, Australia, May 21-25, 2018}, pages = {2433--2439}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/ICRA.2018.8460675}, doi = {10.1109/ICRA.2018.8460675}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/KoertMNP18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/AkrourV0N18, author = {Riad Akrour and Filipe Veiga and Jan Peters and Gerhard Neumann}, title = {Regularizing Reinforcement Learning with State Abstraction}, booktitle = {2018 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2018, Madrid, Spain, October 1-5, 2018}, pages = {534--539}, publisher = {{IEEE}}, year = {2018}, url = {https://doi.org/10.1109/IROS.2018.8594201}, doi = {10.1109/IROS.2018.8594201}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/AkrourV0N18.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1801-00056, author = {Boris Belousov and Jan Peters}, title = {f-Divergence constrained policy improvement}, journal = {CoRR}, volume = {abs/1801.00056}, year = {2018}, url = {http://arxiv.org/abs/1801.00056}, eprinttype = {arXiv}, eprint = {1801.00056}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1801-00056.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1802-08013, author = {Daniel Tanneberg and Jan Peters and Elmar Rueckert}, title = {Intrinsic Motivation and Mental Replay enable Efficient Online Adaptation in Stochastic Recurrent Networks}, journal = {CoRR}, volume = {abs/1802.08013}, year = {2018}, url = {http://arxiv.org/abs/1802.08013}, eprinttype = {arXiv}, eprint = {1802.08013}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1802-08013.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1803-00444, author = {Adrian Sosic and Elmar Rueckert and Jan Peters and Abdelhak M. Zoubir and Heinz Koeppl}, title = {Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling}, journal = {CoRR}, volume = {abs/1803.00444}, year = {2018}, url = {http://arxiv.org/abs/1803.00444}, eprinttype = {arXiv}, eprint = {1803.00444}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1803-00444.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1806-05031, author = {Filipe Veiga and Benoni B. Edin and Jan Peters}, title = {In-Hand Object Stabilization by Independent Finger Control}, journal = {CoRR}, volume = {abs/1806.05031}, year = {2018}, url = {http://arxiv.org/abs/1806.05031}, eprinttype = {arXiv}, eprint = {1806.05031}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1806-05031.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1807-01918, author = {Okan Koc and Guilherme Maeda and Jan Peters}, title = {Optimizing Execution of Dynamic Goal-Directed Robot Movements with Learning Control}, journal = {CoRR}, volume = {abs/1807.01918}, year = {2018}, url = {http://arxiv.org/abs/1807.01918}, eprinttype = {arXiv}, eprint = {1807.01918}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1807-01918.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1808-10648, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Gerhard Neumann and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Adaptation and Robust Learning of Probabilistic Movement Primitives}, journal = {CoRR}, volume = {abs/1808.10648}, year = {2018}, url = {http://arxiv.org/abs/1808.10648}, eprinttype = {arXiv}, eprint = {1808.10648}, timestamp = {Mon, 03 Sep 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1808-10648.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1810-12950, author = {Okan Koc and Jan Peters}, title = {Learning to serve: an experimental study for a new learning from demonstrations framework}, journal = {CoRR}, volume = {abs/1810.12950}, year = {2018}, url = {http://arxiv.org/abs/1810.12950}, eprinttype = {arXiv}, eprint = {1810.12950}, timestamp = {Thu, 08 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1810-12950.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1811-06711, author = {Takayuki Osa and Joni Pajarinen and Gerhard Neumann and J. Andrew Bagnell and Pieter Abbeel and Jan Peters}, title = {An Algorithmic Perspective on Imitation Learning}, journal = {CoRR}, volume = {abs/1811.06711}, year = {2018}, url = {http://arxiv.org/abs/1811.06711}, eprinttype = {arXiv}, eprint = {1811.06711}, timestamp = {Sun, 25 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1811-06711.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1812-08288, author = {Simone Parisi and Voot Tangkaratt and Jan Peters and Mohammad Emtiyaz Khan}, title = {TD-Regularized Actor-Critic Methods}, journal = {CoRR}, volume = {abs/1812.08288}, year = {2018}, url = {http://arxiv.org/abs/1812.08288}, eprinttype = {arXiv}, eprint = {1812.08288}, timestamp = {Wed, 02 Jan 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/abs-1812-08288.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ai/WangBMSP17, author = {Zhikun Wang and Abdeslam Boularias and Katharina M{\"{u}}lling and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Anticipatory action selection for human-robot table tennis}, journal = {Artif. Intell.}, volume = {247}, pages = {399--414}, year = {2017}, url = {https://doi.org/10.1016/j.artint.2014.11.007}, doi = {10.1016/J.ARTINT.2014.11.007}, timestamp = {Fri, 30 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ai/WangBMSP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ai/KupcsikDPLVN17, author = {Andras Gabor Kupcsik and Marc Peter Deisenroth and Jan Peters and Ai Poh Loh and Prahlad Vadakkepat and Gerhard Neumann}, title = {Model-based contextual policy search for data-efficient generalization of robot skills}, journal = {Artif. Intell.}, volume = {247}, pages = {415--439}, year = {2017}, url = {https://doi.org/10.1016/j.artint.2014.11.005}, doi = {10.1016/J.ARTINT.2014.11.005}, timestamp = {Tue, 16 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ai/KupcsikDPLVN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/MaedaNELKP17, author = {Guilherme Maeda and Gerhard Neumann and Marco Ewerton and Rudolf Lioutikov and Oliver Kroemer and Jan Peters}, title = {Probabilistic movement primitives for coordination of multiple human-robot collaborative tasks}, journal = {Auton. Robots}, volume = {41}, number = {3}, pages = {593--612}, year = {2017}, url = {https://doi.org/10.1007/s10514-016-9556-2}, doi = {10.1007/S10514-016-9556-2}, timestamp = {Fri, 30 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/arobots/MaedaNELKP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/firai/DermyPE0CI17, author = {Oriane Dermy and Alexandros Paraschos and Marco Ewerton and Jan Peters and Fran{\c{c}}ois Charpillet and Serena Ivaldi}, title = {Prediction of Intention during Interaction with iCub with Probabilistic Movement Primitives}, journal = {Frontiers Robotics {AI}}, volume = {4}, pages = {45}, year = {2017}, url = {https://doi.org/10.3389/frobt.2017.00045}, doi = {10.3389/FROBT.2017.00045}, timestamp = {Mon, 22 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/firai/DermyPE0CI17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijon/ParisiPP17, author = {Simone Parisi and Matteo Pirotta and Jan Peters}, title = {Manifold-based multi-objective policy search with sample reuse}, journal = {Neurocomputing}, volume = {263}, pages = {3--14}, year = {2017}, url = {https://doi.org/10.1016/j.neucom.2016.11.094}, doi = {10.1016/J.NEUCOM.2016.11.094}, timestamp = {Mon, 07 Aug 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijon/ParisiPP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/LioutikovNMP17, author = {Rudolf Lioutikov and Gerhard Neumann and Guilherme Maeda and Jan Peters}, title = {Learning movement primitive libraries through probabilistic segmentation}, journal = {Int. J. Robotics Res.}, volume = {36}, number = {8}, pages = {879--894}, year = {2017}, url = {https://doi.org/10.1177/0278364917713116}, doi = {10.1177/0278364917713116}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/LioutikovNMP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/MaedaENLP17, author = {Guilherme Maeda and Marco Ewerton and Gerhard Neumann and Rudolf Lioutikov and Jan Peters}, title = {Phase estimation for fast action recognition and trajectory generation in human-robot collaboration}, journal = {Int. J. Robotics Res.}, volume = {36}, number = {13-14}, pages = {1579--1594}, year = {2017}, url = {https://doi.org/10.1177/0278364917693927}, doi = {10.1177/0278364917693927}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/MaedaENLP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijsr/IvaldiL0CPZ17, author = {Serena Ivaldi and S{\'{e}}bastien Lefort and Jan Peters and Mohamed Chetouani and Joelle Provasi and Elisabetta Zibetti}, title = {Towards Engagement Models that Consider Individual Factors in {HRI:} On the Relation of Extroversion and Negative Attitude Towards Robots to Gaze and Speech During a Human-Robot Assembly Task - Experiments with the iCub humanoid}, journal = {Int. J. Soc. Robotics}, volume = {9}, number = {1}, pages = {63--86}, year = {2017}, url = {https://doi.org/10.1007/s12369-016-0357-8}, doi = {10.1007/S12369-016-0357-8}, timestamp = {Sat, 25 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijsr/IvaldiL0CPZ17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/HoofNP17, author = {Herke van Hoof and Gerhard Neumann and Jan Peters}, title = {Non-parametric Policy Search with Limited Information Loss}, journal = {J. Mach. Learn. Res.}, volume = {18}, pages = {73:1--73:46}, year = {2017}, url = {http://jmlr.org/papers/v18/16-142.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/HoofNP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/VinogradskaBNP17, author = {Julia Vinogradska and Bastian Bischoff and Duy Nguyen{-}Tuong and Jan Peters}, title = {Stability of Controllers for Gaussian Process Dynamics}, journal = {J. Mach. Learn. Res.}, volume = {18}, pages = {100:1--100:37}, year = {2017}, url = {http://jmlr.org/papers/v18/16-590.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/VinogradskaBNP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/HoofTP17, author = {Herke van Hoof and Daniel Tanneberg and Jan Peters}, title = {Generalized exploration in policy search}, journal = {Mach. Learn.}, volume = {106}, number = {9-10}, pages = {1705--1724}, year = {2017}, url = {https://doi.org/10.1007/s10994-017-5657-1}, doi = {10.1007/S10994-017-5657-1}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/HoofTP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/OsaESL0N17, author = {Takayuki Osa and Amir Masoud Ghalamzan Esfahani and Rustam Stolkin and Rudolf Lioutikov and Jan Peters and Gerhard Neumann}, title = {Guiding Trajectory Optimization by Demonstrated Distributions}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {2}, number = {2}, pages = {819--826}, year = {2017}, url = {https://doi.org/10.1109/LRA.2017.2653850}, doi = {10.1109/LRA.2017.2653850}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/OsaESL0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/Kroemer017, author = {Oliver Kroemer and Jan Peters}, title = {A Comparison of Autoregressive Hidden Markov Models for Multimodal Manipulations With Variable Masses}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {2}, number = {2}, pages = {1101--1108}, year = {2017}, url = {https://doi.org/10.1109/LRA.2017.2660541}, doi = {10.1109/LRA.2017.2660541}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/Kroemer017.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/ParaschosLPN17, author = {Alexandros Paraschos and Rudolf Lioutikov and Jan Peters and Gerhard Neumann}, title = {Probabilistic Prioritization of Movement Primitives}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {2}, number = {4}, pages = {2294--2301}, year = {2017}, url = {https://doi.org/10.1109/LRA.2017.2725440}, doi = {10.1109/LRA.2017.2725440}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/ParaschosLPN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/PadoisIBMPN17, author = {Vincent Padois and Serena Ivaldi and Jan Babic and Michael N. Mistry and Jan Peters and Francesco Nori}, title = {Whole-body multi-contact motion in humans and humanoids: Advances of the CoDyCo European project}, journal = {Robotics Auton. Syst.}, volume = {90}, pages = {97--117}, year = {2017}, url = {https://doi.org/10.1016/j.robot.2016.08.017}, doi = {10.1016/J.ROBOT.2016.08.017}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/PadoisIBMPN17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/TangkarattHPN0S17, author = {Voot Tangkaratt and Herke van Hoof and Simone Parisi and Gerhard Neumann and Jan Peters and Masashi Sugiyama}, editor = {Satinder Singh and Shaul Markovitch}, title = {Policy Search with High-Dimensional Context Variables}, booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence, February 4-9, 2017, San Francisco, California, {USA}}, pages = {2632--2638}, publisher = {{AAAI} Press}, year = {2017}, url = {https://doi.org/10.1609/aaai.v31i1.10911}, doi = {10.1609/AAAI.V31I1.10911}, timestamp = {Sat, 21 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/TangkarattHPN0S17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aips/AbdulsamadA0N17, author = {Hany Abdulsamad and Oleg Arenz and Jan Peters and Gerhard Neumann}, editor = {Laura Barbulescu and Jeremy Frank and Mausam and Stephen F. Smith}, title = {State-Regularized Policy Search for Linearized Dynamical Systems}, booktitle = {Proceedings of the Twenty-Seventh International Conference on Automated Planning and Scheduling, {ICAPS} 2017, Pittsburgh, Pennsylvania, USA, June 18-23, 2017}, pages = {419--424}, publisher = {{AAAI} Press}, year = {2017}, url = {https://aaai.org/ocs/index.php/ICAPS/ICAPS17/paper/view/15755}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aips/AbdulsamadA0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/MaedaEOB017, author = {Guilherme Maeda and Marco Ewerton and Takayuki Osa and Baptiste Busch and Jan Peters}, title = {Active Incremental Learning of Robot Movement Primitives}, booktitle = {1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, California, USA, November 13-15, 2017, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {78}, pages = {37--46}, publisher = {{PMLR}}, year = {2017}, url = {http://proceedings.mlr.press/v78/maeda17a.html}, timestamp = {Wed, 03 Apr 2019 18:17:24 +0200}, biburl = {https://dblp.org/rec/conf/corl/MaedaEOB017.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/corl/Tanneberg0R17, author = {Daniel Tanneberg and Jan Peters and Elmar Rueckert}, title = {Online Learning with Stochastic Recurrent Neural Networks using Intrinsic Motivation Signals}, booktitle = {1st Annual Conference on Robot Learning, CoRL 2017, Mountain View, California, USA, November 13-15, 2017, Proceedings}, series = {Proceedings of Machine Learning Research}, volume = {78}, pages = {167--174}, publisher = {{PMLR}}, year = {2017}, url = {http://proceedings.mlr.press/v78/tanneberg17a.html}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/corl/Tanneberg0R17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gbcic/FiebigJHB0G17, author = {Karl{-}Heinz Fiebig and Vinay Jayaram and Thomas Hesse and Alexander Blank and Jan Peters and Moritz Grosse{-}Wentrup}, editor = {Gernot R. M{\"{u}}ller{-}Putz and David Steyrl and Selina C. Wriessnegger and Reinhold Scherer}, title = {Bayesian Regression for Artifact correction in Electroencephalography}, booktitle = {From Vision to Reality - Proceedings of the 7th Graz Brain-Computer Interface Conference, {GBCIC} 2017, Graz, Steiermark, Austria, September 18-22, 2017}, publisher = {Verlag der Technischen Universitaet Graz}, year = {2017}, url = {https://doi.org/10.3217/978-3-85125-533-1-25}, doi = {10.3217/978-3-85125-533-1-25}, timestamp = {Mon, 15 Mar 2021 09:34:58 +0100}, biburl = {https://dblp.org/rec/conf/gbcic/FiebigJHB0G17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gbcic/GrossbergerH0G17, author = {Lukas Gro{\ss}berger and Matthias R. Hohmann and Jan Peters and Moritz Grosse{-}Wentrup}, editor = {Gernot R. M{\"{u}}ller{-}Putz and David Steyrl and Selina C. Wriessnegger and Reinhold Scherer}, title = {Investigating Music imagery as a Cognitive Paradigm for low-Cost brain-Computer Interfaces}, booktitle = {From Vision to Reality - Proceedings of the 7th Graz Brain-Computer Interface Conference, {GBCIC} 2017, Graz, Steiermark, Austria, September 18-22, 2017}, publisher = {Verlag der Technischen Universitaet Graz}, year = {2017}, url = {https://doi.org/10.3217/978-3-85125-533-1-30}, doi = {10.3217/978-3-85125-533-1-30}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/gbcic/GrossbergerH0G17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/Tanneberg0R17, author = {Daniel Tanneberg and Jan Peters and Elmar Rueckert}, title = {Efficient online adaptation with stochastic recurrent neural networks}, booktitle = {17th {IEEE-RAS} International Conference on Humanoid Robotics, Humanoids 2017, Birmingham, United Kingdom, November 15-17, 2017}, pages = {198--204}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/HUMANOIDS.2017.8246875}, doi = {10.1109/HUMANOIDS.2017.8246875}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/Tanneberg0R17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/StarkPR17, author = {Svenja Stark and Jan Peters and Elmar Rueckert}, title = {A comparison of distance measures for learning nonparametric motor skill libraries}, booktitle = {17th {IEEE-RAS} International Conference on Humanoid Robotics, Humanoids 2017, Birmingham, United Kingdom, November 15-17, 2017}, pages = {624--630}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/HUMANOIDS.2017.8246937}, doi = {10.1109/HUMANOIDS.2017.8246937}, timestamp = {Wed, 25 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/StarkPR17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/RueckertNTP17, author = {Elmar Rueckert and Moritz Nakatenus and Samuele Tosatto and Jan Peters}, title = {Learning inverse dynamics models in O(n) time with {LSTM} networks}, booktitle = {17th {IEEE-RAS} International Conference on Humanoid Robotics, Humanoids 2017, Birmingham, United Kingdom, November 15-17, 2017}, pages = {811--816}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/HUMANOIDS.2017.8246965}, doi = {10.1109/HUMANOIDS.2017.8246965}, timestamp = {Wed, 25 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/RueckertNTP17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/AkrourS0N17, author = {Riad Akrour and Dmitry Sorokin and Jan Peters and Gerhard Neumann}, editor = {Doina Precup and Yee Whye Teh}, title = {Local Bayesian Optimization of Motor Skills}, booktitle = {Proceedings of the 34th International Conference on Machine Learning, {ICML} 2017, Sydney, NSW, Australia, 6-11 August 2017}, series = {Proceedings of Machine Learning Research}, volume = {70}, pages = {41--50}, publisher = {{PMLR}}, year = {2017}, url = {http://proceedings.mlr.press/v70/akrour17a.html}, timestamp = {Wed, 29 May 2019 08:41:45 +0200}, biburl = {https://dblp.org/rec/conf/icml/AkrourS0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/Abi-FarrajOPPNG17, author = {Firas Abi{-}Farraj and Takayuki Osa and Nicolo Pedemonte and Jan Peters and Gerhard Neumann and Paolo Robuffo Giordano}, title = {A learning-based shared control architecture for interactive task execution}, booktitle = {2017 {IEEE} International Conference on Robotics and Automation, {ICRA} 2017, Singapore, Singapore, May 29 - June 3, 2017}, pages = {329--335}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICRA.2017.7989042}, doi = {10.1109/ICRA.2017.7989042}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/Abi-FarrajOPPNG17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/WilbersL017, author = {Daniel Wilbers and Rudolf Lioutikov and Jan Peters}, title = {Context-driven movement primitive adaptation}, booktitle = {2017 {IEEE} International Conference on Robotics and Automation, {ICRA} 2017, Singapore, Singapore, May 29 - June 3, 2017}, pages = {3469--3475}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICRA.2017.7989396}, doi = {10.1109/ICRA.2017.7989396}, timestamp = {Wed, 26 Jul 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/WilbersL017.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/GabrielA0N17, author = {Alexander Gabriel and Riad Akrour and Jan Peters and Gerhard Neumann}, title = {Empowered skills}, booktitle = {2017 {IEEE} International Conference on Robotics and Automation, {ICRA} 2017, Singapore, Singapore, May 29 - June 3, 2017}, pages = {6435--6441}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICRA.2017.7989760}, doi = {10.1109/ICRA.2017.7989760}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/GabrielA0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/EndA0N17, author = {Felix End and Riad Akrour and Jan Peters and Gerhard Neumann}, title = {Layered direct policy search for learning hierarchical skills}, booktitle = {2017 {IEEE} International Conference on Robotics and Automation, {ICRA} 2017, Singapore, Singapore, May 29 - June 3, 2017}, pages = {6442--6448}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/ICRA.2017.7989761}, doi = {10.1109/ICRA.2017.7989761}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/EndA0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ParisiR017, author = {Simone Parisi and Simon Ramstedt and Jan Peters}, title = {Goal-driven dimensionality reduction for reinforcement learning}, booktitle = {2017 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2017, Vancouver, BC, Canada, September 24-28, 2017}, pages = {4634--4639}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IROS.2017.8206334}, doi = {10.1109/IROS.2017.8206334}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/ParisiR017.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/PajarinenKKS0N17, author = {Joni Pajarinen and Ville Kyrki and Michael C. Koval and Siddhartha S. Srinivasa and Jan Peters and Gerhard Neumann}, title = {Hybrid control trajectory optimization under uncertainty}, booktitle = {2017 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2017, Vancouver, BC, Canada, September 24-28, 2017}, pages = {5694--5701}, publisher = {{IEEE}}, year = {2017}, url = {https://doi.org/10.1109/IROS.2017.8206460}, doi = {10.1109/IROS.2017.8206460}, timestamp = {Sat, 09 Apr 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/PajarinenKKS0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:reference/ml/0001B17, author = {Jan Peters and J. Andrew Bagnell}, editor = {Claude Sammut and Geoffrey I. Webb}, title = {Policy Gradient Methods}, booktitle = {Encyclopedia of Machine Learning and Data Mining}, pages = {982--985}, publisher = {Springer}, year = {2017}, url = {https://doi.org/10.1007/978-1-4899-7687-1\_646}, doi = {10.1007/978-1-4899-7687-1\_646}, timestamp = {Wed, 12 Jul 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/reference/ml/0001B17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:reference/ml/0001TRM17, author = {Jan Peters and Russ Tedrake and Nick Roy and Jun Morimoto}, editor = {Claude Sammut and Geoffrey I. Webb}, title = {Robot Learning}, booktitle = {Encyclopedia of Machine Learning and Data Mining}, pages = {1106--1109}, publisher = {Springer}, year = {2017}, url = {https://doi.org/10.1007/978-1-4899-7687-1\_738}, doi = {10.1007/978-1-4899-7687-1\_738}, timestamp = {Wed, 12 Jul 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/reference/ml/0001TRM17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/PajarinenKKS0N17, author = {Joni Pajarinen and Ville Kyrki and Michael C. Koval and Siddhartha S. Srinivasa and Jan Peters and Gerhard Neumann}, title = {Hybrid control trajectory optimization under uncertainty}, journal = {CoRR}, volume = {abs/1702.04396}, year = {2017}, url = {http://arxiv.org/abs/1702.04396}, eprinttype = {arXiv}, eprint = {1702.04396}, timestamp = {Wed, 24 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/PajarinenKKS0N17.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/amai/CalandraSPD16, author = {Roberto Calandra and Andr{\'{e}} Seyfarth and Jan Peters and Marc Peter Deisenroth}, title = {Bayesian optimization for learning gaits under uncertainty - An experimental comparison on a dynamic bipedal walker}, journal = {Ann. Math. Artif. Intell.}, volume = {76}, number = {1-2}, pages = {5--23}, year = {2016}, url = {https://doi.org/10.1007/s10472-015-9463-9}, doi = {10.1007/S10472-015-9463-9}, timestamp = {Mon, 05 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/amai/CalandraSPD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jirs/AbdolmalekiLR0N16, author = {Abbas Abdolmaleki and Nuno Lau and Lu{\'{\i}}s Paulo Reis and Jan Peters and Gerhard Neumann}, title = {Contextual Policy Search for Linear and Nonlinear Generalization of a Humanoid Walking Controller}, journal = {J. Intell. Robotic Syst.}, volume = {83}, number = {3-4}, pages = {393--408}, year = {2016}, url = {https://doi.org/10.1007/s10846-016-0347-y}, doi = {10.1007/S10846-016-0347-Y}, timestamp = {Tue, 07 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jirs/AbdolmalekiLR0N16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/DanielNKP16, author = {Christian Daniel and Gerhard Neumann and Oliver Kroemer and Jan Peters}, title = {Hierarchical Relative Entropy Policy Search}, journal = {J. Mach. Learn. Res.}, volume = {17}, pages = {93:1--93:50}, year = {2016}, url = {http://jmlr.org/papers/v17/15-188.html}, timestamp = {Wed, 10 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/DanielNKP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/DanielHPN16, author = {Christian Daniel and Herke van Hoof and Jan Peters and Gerhard Neumann}, title = {Probabilistic inference for determining options in reinforcement learning}, journal = {Mach. Learn.}, volume = {104}, number = {2-3}, pages = {337--357}, year = {2016}, url = {https://doi.org/10.1007/s10994-016-5580-x}, doi = {10.1007/S10994-016-5580-X}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/DanielHPN16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ral/MaedaEK016, author = {Guilherme Maeda and Marco Ewerton and Dorothea Koert and Jan Peters}, title = {Acquiring and Generalizing the Embodiment Mapping From Human Observations to Robot Skills}, journal = {{IEEE} Robotics Autom. Lett.}, volume = {1}, number = {2}, pages = {784--791}, year = {2016}, url = {https://doi.org/10.1109/LRA.2016.2525038}, doi = {10.1109/LRA.2016.2525038}, timestamp = {Thu, 02 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ral/MaedaEK016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaaifs/MaedaMEL016, author = {Guilherme Maeda and Aayush Maloo and Marco Ewerton and Rudolf Lioutikov and Jan Peters}, title = {Anticipative Interaction Primitives for Human-Robot Collaboration}, booktitle = {2016 {AAAI} Fall Symposia, Arlington, Virginia, USA, November 17-19, 2016}, publisher = {{AAAI} Press}, year = {2016}, url = {http://aaai.org/ocs/index.php/FSS/FSS16/paper/view/14067}, timestamp = {Wed, 14 Nov 2018 14:49:10 +0100}, biburl = {https://dblp.org/rec/conf/aaaifs/MaedaMEL016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/gecco/AbdolmalekiLLR016, author = {Abbas Abdolmaleki and Rudolf Lioutikov and Nuno Lau and Lu{\'{\i}}s Paulo Reis and Jan Peters and Gerhard Neumann}, editor = {Tobias Friedrich and Frank Neumann and Andrew M. Sutton}, title = {Model-Based Relative Entropy Stochastic Search}, booktitle = {Genetic and Evolutionary Computation Conference, {GECCO} 2016, Denver, CO, USA, July 20-24, 2016, Companion Material Proceedings}, pages = {153--154}, publisher = {{ACM}}, year = {2016}, url = {https://doi.org/10.1145/2908961.2930952}, doi = {10.1145/2908961.2930952}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/gecco/AbdolmalekiLLR016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/EwertonMKW016, author = {Marco Ewerton and Guilherme Maeda and Gerrit Kollegger and Josef Wiemeyer and Jan Peters}, title = {Incremental imitation learning of context-dependent motor skills}, booktitle = {16th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, November 15-17, 2016}, pages = {351--358}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/HUMANOIDS.2016.7803300}, doi = {10.1109/HUMANOIDS.2016.7803300}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/EwertonMKW016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/Gomez-GonzalezN16, author = {Sebasti{\'{a}}n G{\'{o}}mez{-}Gonz{\'{a}}lez and Gerhard Neumann and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Using probabilistic movement primitives for striking movements}, booktitle = {16th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, November 15-17, 2016}, pages = {502--508}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/HUMANOIDS.2016.7803322}, doi = {10.1109/HUMANOIDS.2016.7803322}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/Gomez-GonzalezN16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/KoertMLN016, author = {Dorothea Koert and Guilherme Maeda and Rudolf Lioutikov and Gerhard Neumann and Jan Peters}, title = {Demonstration based trajectory optimization for generalizable robot motions}, booktitle = {16th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, November 15-17, 2016}, pages = {515--522}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/HUMANOIDS.2016.7803324}, doi = {10.1109/HUMANOIDS.2016.7803324}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/KoertMLN016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/HuangBKS016, author = {Yanlong Huang and Dieter Buchler and Okan Koc and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Jointly learning trajectory generation and hitting point prediction in robot table tennis}, booktitle = {16th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, November 15-17, 2016}, pages = {650--655}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/HUMANOIDS.2016.7803343}, doi = {10.1109/HUMANOIDS.2016.7803343}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/HuangBKS016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/TannebergP0R16, author = {Daniel Tanneberg and Alexandros Paraschos and Jan Peters and Elmar Rueckert}, title = {Deep spiking networks for model-based planning in humanoids}, booktitle = {16th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2016, Cancun, Mexico, November 15-17, 2016}, pages = {656--661}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/HUMANOIDS.2016.7803344}, doi = {10.1109/HUMANOIDS.2016.7803344}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/TannebergP0R16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/VinogradskaBNRS16, author = {Julia Vinogradska and Bastian Bischoff and Duy Nguyen{-}Tuong and Anne Romer and Henner Schmidt and Jan Peters}, editor = {Maria{-}Florina Balcan and Kilian Q. Weinberger}, title = {Stability of Controllers for Gaussian Process Forward Models}, booktitle = {Proceedings of the 33nd International Conference on Machine Learning, {ICML} 2016, New York City, NY, USA, June 19-24, 2016}, series = {{JMLR} Workshop and Conference Proceedings}, volume = {48}, pages = {545--554}, publisher = {JMLR.org}, year = {2016}, url = {http://proceedings.mlr.press/v48/vinogradska16.html}, timestamp = {Wed, 29 May 2019 08:41:46 +0200}, biburl = {https://dblp.org/rec/conf/icml/VinogradskaBNRS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/EwertonMNKKW016, author = {Marco Ewerton and Guilherme Maeda and Gerhard Neumann and Viktor Kisner and Gerrit Kollegger and Josef Wiemeyer and Jan Peters}, editor = {Danica Kragic and Antonio Bicchi and Alessandro De Luca}, title = {Movement primitives with multiple phase parameters}, booktitle = {2016 {IEEE} International Conference on Robotics and Automation, {ICRA} 2016, Stockholm, Sweden, May 16-21, 2016}, pages = {201--206}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICRA.2016.7487134}, doi = {10.1109/ICRA.2016.7487134}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/EwertonMNKKW016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/ModugnoNRO0I16, author = {Valerio Modugno and Gerhard Neumann and Elmar Rueckert and Giuseppe Oriolo and Jan Peters and Serena Ivaldi}, editor = {Danica Kragic and Antonio Bicchi and Alessandro De Luca}, title = {Learning soft task priorities for control of redundant robots}, booktitle = {2016 {IEEE} International Conference on Robotics and Automation, {ICRA} 2016, Stockholm, Sweden, May 16-21, 2016}, pages = {221--226}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICRA.2016.7487137}, doi = {10.1109/ICRA.2016.7487137}, timestamp = {Mon, 05 Feb 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/ModugnoNRO0I16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/BuchlerOP16, author = {Dieter Buchler and Heiko Ott and Jan Peters}, editor = {Danica Kragic and Antonio Bicchi and Alessandro De Luca}, title = {A lightweight robotic arm with pneumatic muscles for robot learning}, booktitle = {2016 {IEEE} International Conference on Robotics and Automation, {ICRA} 2016, Stockholm, Sweden, May 16-21, 2016}, pages = {4086--4092}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ICRA.2016.7487599}, doi = {10.1109/ICRA.2016.7487599}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/BuchlerOP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/Calandra0RD16, author = {Roberto Calandra and Jan Peters and Carl Edward Rasmussen and Marc Peter Deisenroth}, title = {Manifold Gaussian Processes for regression}, booktitle = {2016 International Joint Conference on Neural Networks, {IJCNN} 2016, Vancouver, BC, Canada, July 24-29, 2016}, pages = {3338--3345}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/IJCNN.2016.7727626}, doi = {10.1109/IJCNN.2016.7727626}, timestamp = {Wed, 16 Oct 2019 14:14:55 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/Calandra0RD16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KocM016, author = {Okan Koc and Guilherme Maeda and Jan Peters}, title = {A new trajectory generation framework in robotic table tennis}, booktitle = {2016 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2016, Daejeon, South Korea, October 9-14, 2016}, pages = {3750--3756}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/IROS.2016.7759552}, doi = {10.1109/IROS.2016.7759552}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/KocM016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ManschitzGK016, author = {Simon Manschitz and Michael Gienger and Jens Kober and Jan Peters}, title = {Probabilistic decomposition of sequential force interaction tasks into Movement Primitives}, booktitle = {2016 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2016, Daejeon, South Korea, October 9-14, 2016}, pages = {3920--3927}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/IROS.2016.7759577}, doi = {10.1109/IROS.2016.7759577}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/ManschitzGK016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/HoofCKS016, author = {Herke van Hoof and Nutan Chen and Maximilian Karl and Patrick van der Smagt and Jan Peters}, title = {Stable reinforcement learning with autoencoders for tactile and visual data}, booktitle = {2016 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2016, Daejeon, South Korea, October 9-14, 2016}, pages = {3928--3934}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/IROS.2016.7759578}, doi = {10.1109/IROS.2016.7759578}, timestamp = {Thu, 14 Oct 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/HoofCKS016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/YiCVHHZ016, author = {Zhengkun Yi and Roberto Calandra and Filipe Veiga and Herke van Hoof and Tucker Hermans and Yilei Zhang and Jan Peters}, title = {Active tactile object exploration with Gaussian processes}, booktitle = {2016 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2016, Daejeon, South Korea, October 9-14, 2016}, pages = {4925--4930}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/IROS.2016.7759723}, doi = {10.1109/IROS.2016.7759723}, timestamp = {Sat, 16 Sep 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/YiCVHHZ016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iser/Osa0N16, author = {Takayuki Osa and Jan Peters and Gerhard Neumann}, editor = {Dana Kulic and Yoshihiko Nakamura and Oussama Khatib and Gentiane Venture}, title = {Experiments with Hierarchical Reinforcement Learning of Multiple Grasping Policies}, booktitle = {International Symposium on Experimental Robotics, {ISER} 2016, Tokyo, Japan, October 3-6, 2016}, series = {Springer Proceedings in Advanced Robotics}, volume = {1}, pages = {160--172}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-50115-4\_15}, doi = {10.1007/978-3-319-50115-4\_15}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iser/Osa0N16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BelousovNRP16, author = {Boris Belousov and Gerhard Neumann and Constantin A. Rothkopf and Jan Peters}, editor = {Daniel D. Lee and Masashi Sugiyama and Ulrike von Luxburg and Isabelle Guyon and Roman Garnett}, title = {Catching heuristics are optimal control policies}, booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016, December 5-10, 2016, Barcelona, Spain}, pages = {1426--1434}, year = {2016}, url = {https://proceedings.neurips.cc/paper/2016/hash/43fa7f58b7eac7ac872209342e62e8f1-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/BelousovNRP16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ro-man/WeberRC0B16, author = {Paul Weber and Elmar Rueckert and Roberto Calandra and Jan Peters and Philipp Beckerle}, title = {A low-cost sensor glove with vibrotactile feedback and multiple finger joint and hand motion sensing for human-robot interaction}, booktitle = {25th {IEEE} International Symposium on Robot and Human Interactive Communication, {RO-MAN} 2016, New York, NY, USA, August 26-31, 2016}, pages = {99--104}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/ROMAN.2016.7745096}, doi = {10.1109/ROMAN.2016.7745096}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ro-man/WeberRC0B16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/smc/FiebigJ0G16, author = {Karl{-}Heinz Fiebig and Vinay Jayaram and Jan Peters and Moritz Grosse{-}Wentrup}, title = {Multi-task logistic regression in brain-computer interfaces}, booktitle = {2016 {IEEE} International Conference on Systems, Man, and Cybernetics, {SMC} 2016, Budapest, Hungary, October 9-12, 2016}, pages = {2307--2312}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/SMC.2016.7844582}, doi = {10.1109/SMC.2016.7844582}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/smc/FiebigJ0G16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ssci/ParisiBV016, author = {Simone Parisi and Alexander Blank and Tobias Viernickel and Jan Peters}, title = {Local-utopia policy selection for multi-objective reinforcement learning}, booktitle = {2016 {IEEE} Symposium Series on Computational Intelligence, {SSCI} 2016, Athens, Greece, December 6-9, 2016}, pages = {1--7}, publisher = {{IEEE}}, year = {2016}, url = {https://doi.org/10.1109/SSCI.2016.7849369}, doi = {10.1109/SSCI.2016.7849369}, timestamp = {Wed, 16 Oct 2019 14:14:56 +0200}, biburl = {https://dblp.org/rec/conf/ssci/ParisiBV016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:reference/robo/0001LKNBS16, author = {Jan Peters and Daniel D. Lee and Jens Kober and Duy Nguyen{-}Tuong and J. Andrew Bagnell and Stefan Schaal}, editor = {Bruno Siciliano and Oussama Khatib}, title = {Robot Learning}, booktitle = {Springer Handbook of Robotics}, series = {Springer Handbooks}, pages = {357--398}, publisher = {Springer}, year = {2016}, url = {https://doi.org/10.1007/978-3-319-32552-1\_15}, doi = {10.1007/978-3-319-32552-1\_15}, timestamp = {Sun, 25 Jul 2021 11:43:37 +0200}, biburl = {https://dblp.org/rec/reference/robo/0001LKNBS16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/TangkarattHPN0S16, author = {Voot Tangkaratt and Herke van Hoof and Simone Parisi and Gerhard Neumann and Jan Peters and Masashi Sugiyama}, title = {Policy Search with High-Dimensional Context Variables}, journal = {CoRR}, volume = {abs/1611.03231}, year = {2016}, url = {http://arxiv.org/abs/1611.03231}, eprinttype = {arXiv}, eprint = {1611.03231}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/TangkarattHPN0S16.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/Veiga016, author = {Filipe Veiga and Jan Peters}, title = {Can Modular Finger Control for In-Hand Object Stabilization be accomplished by Independent Tactile Feedback Control Laws?}, journal = {CoRR}, volume = {abs/1612.08202}, year = {2016}, url = {http://arxiv.org/abs/1612.08202}, eprinttype = {arXiv}, eprint = {1612.08202}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/Veiga016.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/DanielKVM015, author = {Christian Daniel and Oliver Kroemer and Malte Viering and Jan Metz and Jan Peters}, title = {Active reward learning with a novel acquisition function}, journal = {Auton. Robots}, volume = {39}, number = {3}, pages = {389--405}, year = {2015}, url = {https://doi.org/10.1007/s10514-015-9454-z}, doi = {10.1007/S10514-015-9454-Z}, timestamp = {Wed, 26 Jul 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/DanielKVM015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/ManschitzKG015, author = {Simon Manschitz and Jens Kober and Michael Gienger and Jan Peters}, title = {Learning movement primitive attractor goals and sequential skills from kinesthetic demonstrations}, journal = {Robotics Auton. Syst.}, volume = {74}, pages = {97--107}, year = {2015}, url = {https://doi.org/10.1016/j.robot.2015.07.005}, doi = {10.1016/J.ROBOT.2015.07.005}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/ManschitzKG015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aips/DannN015, author = {Christoph Dann and Gerhard Neumann and Jan Peters}, editor = {Ronen I. Brafman and Carmel Domshlak and Patrik Haslum and Shlomo Zilberstein}, title = {Policy Evaluation with Temporal Differences: {A} Survey and Comparison (Extended Abstract)}, booktitle = {Proceedings of the Twenty-Fifth International Conference on Automated Planning and Scheduling, {ICAPS} 2015, Jerusalem, Israel, June 7-11, 2015}, pages = {359--360}, publisher = {{AAAI} Press}, year = {2015}, url = {http://www.aaai.org/ocs/index.php/ICAPS/ICAPS15/paper/view/10635}, timestamp = {Tue, 26 May 2015 21:03:02 +0200}, biburl = {https://dblp.org/rec/conf/aips/DannN015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aistats/Hoof0N15, author = {Herke van Hoof and Jan Peters and Gerhard Neumann}, editor = {Guy Lebanon and S. V. N. Vishwanathan}, title = {Learning of Non-Parametric Control Policies with High-Dimensional State Features}, booktitle = {Proceedings of the Eighteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2015, San Diego, California, USA, May 9-12, 2015}, series = {{JMLR} Workshop and Conference Proceedings}, volume = {38}, publisher = {JMLR.org}, year = {2015}, url = {http://proceedings.mlr.press/v38/vanhoof15.html}, timestamp = {Wed, 29 May 2019 08:41:44 +0200}, biburl = {https://dblp.org/rec/conf/aistats/Hoof0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/KocMN015, author = {Okan Koc and Guilherme Maeda and Gerhard Neumann and Jan Peters}, title = {Optimizing robot striking movement primitives with Iterative Learning Control}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {80--87}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363535}, doi = {10.1109/HUMANOIDS.2015.7363535}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/KocMN015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/HoofHN015, author = {Herke van Hoof and Tucker Hermans and Gerhard Neumann and Jan Peters}, title = {Learning robot in-hand manipulation with tactile features}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {121--127}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363524}, doi = {10.1109/HUMANOIDS.2015.7363524}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/HoofHN015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/Hoelscher0H15, author = {Janine Hoelscher and Jan Peters and Tucker Hermans}, title = {Evaluation of tactile feature extraction for interactive object recognition}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {310--317}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363560}, doi = {10.1109/HUMANOIDS.2015.7363560}, timestamp = {Wed, 17 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/Hoelscher0H15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/LioutikovNM015, author = {Rudolf Lioutikov and Gerhard Neumann and Guilherme Maeda and Jan Peters}, title = {Probabilistic segmentation applied to an assembly task}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {533--540}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363584}, doi = {10.1109/HUMANOIDS.2015.7363584}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/LioutikovNM015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/LeischnigLK015, author = {Simon Leischnig and Stefan Luettgen and Oliver Kroemer and Jan Peters}, title = {A comparison of contact distribution representations for learning to predict object interactions}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {616--622}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363435}, doi = {10.1109/HUMANOIDS.2015.7363435}, timestamp = {Wed, 17 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/LeischnigLK015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/CalandraIDP15, author = {Roberto Calandra and Serena Ivaldi and Marc Peter Deisenroth and Jan Peters}, title = {Learning torque control in presence of contacts using tactile sensing from robot skin}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {690--695}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363429}, doi = {10.1109/HUMANOIDS.2015.7363429}, timestamp = {Thu, 15 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/CalandraIDP15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/FritscheU0C15, author = {Lars Fritsche and Felix Unverzag and Jan Peters and Roberto Calandra}, title = {First-person tele-operation of a humanoid robot}, booktitle = {15th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2015, Seoul, South Korea, November 3-5, 2015}, pages = {997--1002}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/HUMANOIDS.2015.7363475}, doi = {10.1109/HUMANOIDS.2015.7363475}, timestamp = {Sun, 12 Nov 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/FritscheU0C15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icarsc/AbdolmalekiLR0N15, author = {Abbas Abdolmaleki and Nuno Lau and Lu{\'{\i}}s Paulo Reis and Jan Peters and Gerhard Neumann}, title = {Contextual Policy Search for Generalizing a Parameterized Biped Walking Controller}, booktitle = {2015 {IEEE} International Conference on Autonomous Robot Systems and Competitions, {ICARSC} 2015, Vila Real, Portugal, April 8-10, 2015}, pages = {17--22}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICARSC.2015.43}, doi = {10.1109/ICARSC.2015.43}, timestamp = {Wed, 16 Oct 2019 14:14:57 +0200}, biburl = {https://dblp.org/rec/conf/icarsc/AbdolmalekiLR0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KroemerDNH015, author = {Oliver Kroemer and Christian Daniel and Gerhard Neumann and Herke van Hoof and Jan Peters}, title = {Towards learning hierarchical skills for multi-phase manipulation tasks}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2015, Seattle, WA, USA, 26-30 May, 2015}, pages = {1503--1510}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICRA.2015.7139389}, doi = {10.1109/ICRA.2015.7139389}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/KroemerDNH015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/RuckertMP0N15, author = {Elmar Rueckert and Jan Mundo and Alexandros Paraschos and Jan Peters and Gerhard Neumann}, title = {Extracting low-dimensional control variables for movement primitives}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2015, Seattle, WA, USA, 26-30 May, 2015}, pages = {1511--1518}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICRA.2015.7139390}, doi = {10.1109/ICRA.2015.7139390}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/RuckertMP0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/EwertonNLA0M15, author = {Marco Ewerton and Gerhard Neumann and Rudolf Lioutikov and Heni Ben Amor and Jan Peters and Guilherme Maeda}, title = {Learning multiple collaborative tasks with a mixture of Interaction Primitives}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2015, Seattle, WA, USA, 26-30 May, 2015}, pages = {1535--1542}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICRA.2015.7139393}, doi = {10.1109/ICRA.2015.7139393}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/EwertonNLA0M15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/CalandraIDR015, author = {Roberto Calandra and Serena Ivaldi and Marc Peter Deisenroth and Elmar Rueckert and Jan Peters}, title = {Learning inverse dynamics models with contacts}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2015, Seattle, WA, USA, 26-30 May, 2015}, pages = {3186--3191}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/ICRA.2015.7139638}, doi = {10.1109/ICRA.2015.7139638}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/CalandraIDR015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ManschitzKG015, author = {Simon Manschitz and Jens Kober and Michael Gienger and Jan Peters}, title = {Probabilistic progress prediction and sequencing of concurrent movement primitives}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {449--455}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7353411}, doi = {10.1109/IROS.2015.7353411}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/ManschitzKG015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/EwertonM0N15, author = {Marco Ewerton and Guilherme Maeda and Jan Peters and Gerhard Neumann}, title = {Learning motor skills from partially observed movements executed at different speeds}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {456--463}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7353412}, doi = {10.1109/IROS.2015.7353412}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/EwertonM0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/WahrburgZMPD15, author = {Arne Wahrburg and Stefan Zeiss and Bjoern Matthias and Jan Peters and Hao Ding}, title = {Combined pose-wrench and state machine representation for modeling Robotic Assembly Skills}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {852--857}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7353471}, doi = {10.1109/IROS.2015.7353471}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/WahrburgZMPD15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ParaschosR0N15, author = {Alexandros Paraschos and Elmar Rueckert and Jan Peters and Gerhard Neumann}, title = {Model-free Probabilistic Movement Primitives for physical interaction}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {2860--2866}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7353771}, doi = {10.1109/IROS.2015.7353771}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/ParaschosR0N15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/HuangSP15, author = {Yanlong Huang and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning optimal striking points for a ping-pong playing robot}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {4587--4592}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7354030}, doi = {10.1109/IROS.2015.7354030}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/HuangSP15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/VeigaH0H15, author = {Filipe Veiga and Herke van Hoof and Jan Peters and Tucker Hermans}, title = {Stabilizing novel objects by learning to predict tactile slip}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {5065--5072}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7354090}, doi = {10.1109/IROS.2015.7354090}, timestamp = {Sat, 16 Sep 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/VeigaH0H15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ParisiAPD015, author = {Simone Parisi and Hany Abdulsamad and Alexandros Paraschos and Christian Daniel and Jan Peters}, title = {Reinforcement learning vs human programming in tetherball robot games}, booktitle = {2015 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2015, Hamburg, Germany, September 28 - October 2, 2015}, pages = {6428--6434}, publisher = {{IEEE}}, year = {2015}, url = {https://doi.org/10.1109/IROS.2015.7354296}, doi = {10.1109/IROS.2015.7354296}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/ParisiAPD015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isrr/MaedaNELP15, author = {Guilherme Maeda and Gerhard Neumann and Marco Ewerton and Rudolf Lioutikov and Jan Peters}, editor = {Antonio Bicchi and Wolfram Burgard}, title = {A Probabilistic Framework for Semi-autonomous Robots Based on Interaction Primitives with Phase Estimation}, booktitle = {Robotics Research, Proceedings of the 17th International Symposium of Robotics Research, {ISRR} 2015, Sestri Levante, Italy, September 12-15, 2015, Volume 2}, series = {Springer Proceedings in Advanced Robotics}, volume = {3}, pages = {253--268}, publisher = {Springer}, year = {2015}, url = {https://doi.org/10.1007/978-3-319-60916-4\_15}, doi = {10.1007/978-3-319-60916-4\_15}, timestamp = {Mon, 11 Dec 2017 19:15:27 +0100}, biburl = {https://dblp.org/rec/conf/isrr/MaedaNELP15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AbdolmalekiLPLR15, author = {Abbas Abdolmaleki and Rudolf Lioutikov and Jan Peters and Nuno Lau and Lu{\'{\i}}s Paulo Reis and Gerhard Neumann}, editor = {Corinna Cortes and Neil D. Lawrence and Daniel D. Lee and Masashi Sugiyama and Roman Garnett}, title = {Model-Based Relative Entropy Stochastic Search}, booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada}, pages = {3537--3545}, year = {2015}, url = {https://proceedings.neurips.cc/paper/2015/hash/36ac8e558ac7690b6f44e2cb5ef93322-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/AbdolmalekiLPLR15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/IvaldiL0CPZ15, author = {Serena Ivaldi and S{\'{e}}bastien Lefort and Jan Peters and Mohamed Chetouani and Joelle Provasi and Elisabetta Zibetti}, title = {Towards engagement models that consider individual factors in {HRI:} on the relation of extroversion and negative attitude towards robots to gaze and speech during a human-robot assembly task}, journal = {CoRR}, volume = {abs/1508.04603}, year = {2015}, url = {http://arxiv.org/abs/1508.04603}, eprinttype = {arXiv}, eprint = {1508.04603}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/IvaldiL0CPZ15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/RuckertLCSB015, author = {Elmar Rueckert and Rudolf Lioutikov and Roberto Calandra and Marius Schmidt and Philipp Beckerle and Jan Peters}, title = {Low-cost Sensor Glove with Force Feedback for Learning from Demonstrations using Probabilistic Trajectory Representations}, journal = {CoRR}, volume = {abs/1510.03253}, year = {2015}, url = {http://arxiv.org/abs/1510.03253}, eprinttype = {arXiv}, eprint = {1510.03253}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/corr/RuckertLCSB015.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/dagstuhl-reports/PetersPPS15, author = {Jan Peters and Justus H. Piater and Robert Platt Jr. and Siddhartha S. Srinivasa}, title = {Multimodal Manipulation Under Uncertainty (Dagstuhl Seminar 15411)}, journal = {Dagstuhl Reports}, volume = {5}, number = {10}, pages = {1--18}, year = {2015}, url = {https://doi.org/10.4230/DagRep.5.10.1}, doi = {10.4230/DAGREP.5.10.1}, timestamp = {Wed, 24 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/dagstuhl-reports/PetersPPS15.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@book{DBLP:series/star/KoberP14, author = {Jens Kober and Jan Peters}, title = {Learning Motor Skills - From Algorithms to Robot Experiments}, series = {Springer Tracts in Advanced Robotics}, volume = {97}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-03194-1}, doi = {10.1007/978-3-319-03194-1}, isbn = {978-3-319-03193-4}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/series/star/KoberP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ar/BocsiCP14, author = {Botond Attila B{\'{o}}csi and Lehel Csat{\'{o}} and Jan Peters}, title = {Indirect robot model learning for tracking control}, journal = {Adv. Robotics}, volume = {28}, number = {9}, pages = {589--599}, year = {2014}, url = {https://doi.org/10.1080/01691864.2014.888371}, doi = {10.1080/01691864.2014.888371}, timestamp = {Sat, 25 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ar/BocsiCP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/AmorSHP14, author = {Heni Ben Amor and Ashutosh Saxena and Nicolas Hudson and Jan Peters}, title = {Special issue on autonomous grasping and manipulation}, journal = {Auton. Robots}, volume = {36}, number = {1-2}, pages = {1--3}, year = {2014}, url = {https://doi.org/10.1007/s10514-013-9379-3}, doi = {10.1007/S10514-013-9379-3}, timestamp = {Tue, 26 Jun 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/AmorSHP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/bc/MullingBMSP14, author = {Katharina M{\"{u}}lling and Abdeslam Boularias and Betty J. Mohler and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning strategies in table tennis using inverse reinforcement learning}, journal = {Biol. Cybern.}, volume = {108}, number = {5}, pages = {603--619}, year = {2014}, url = {https://doi.org/10.1007/s00422-014-0599-1}, doi = {10.1007/S00422-014-0599-1}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/bc/MullingBMSP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ficn/NeumannDPK014, author = {Gerhard Neumann and Christian Daniel and Alexandros Paraschos and Andras Gabor Kupcsik and Jan Peters}, title = {Learning modular policies for robotics}, journal = {Frontiers Comput. Neurosci.}, volume = {8}, pages = {62}, year = {2014}, url = {https://doi.org/10.3389/fncom.2014.00062}, doi = {10.3389/FNCOM.2014.00062}, timestamp = {Sat, 23 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ficn/NeumannDPK014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jacic/LioutikovPPN14, author = {Rudolf Lioutikov and Alexandros Paraschos and Jan Peters and Gerhard Neumann}, title = {Generalizing Movements with Information-Theoretic Stochastic Optimal Control}, journal = {J. Aerosp. Inf. Syst.}, volume = {11}, number = {9}, pages = {579--595}, year = {2014}, url = {https://doi.org/10.2514/1.I010195}, doi = {10.2514/1.I010195}, timestamp = {Thu, 05 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jacic/LioutikovPPN14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/DannNP14, author = {Christoph Dann and Gerhard Neumann and Jan Peters}, title = {Policy evaluation with temporal differences: a survey and comparison}, journal = {J. Mach. Learn. Res.}, volume = {15}, number = {1}, pages = {809--883}, year = {2014}, url = {https://dl.acm.org/doi/10.5555/2627435.2638563}, doi = {10.5555/2627435.2638563}, timestamp = {Thu, 02 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/DannNP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jmlr/WierstraSGSPS14, author = {Daan Wierstra and Tom Schaul and Tobias Glasmachers and Yi Sun and Jan Peters and J{\"{u}}rgen Schmidhuber}, title = {Natural evolution strategies}, journal = {J. Mach. Learn. Res.}, volume = {15}, number = {1}, pages = {949--980}, year = {2014}, url = {https://dl.acm.org/doi/10.5555/2627435.2638566}, doi = {10.5555/2627435.2638566}, timestamp = {Thu, 02 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/WierstraSGSPS14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/HoofKP14, author = {Herke van Hoof and Oliver Kroemer and Jan Peters}, title = {Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments}, journal = {{IEEE} Trans. Robotics}, volume = {30}, number = {5}, pages = {1198--1209}, year = {2014}, url = {https://doi.org/10.1109/TRO.2014.2334912}, doi = {10.1109/TRO.2014.2334912}, timestamp = {Sat, 16 Sep 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/trob/HoofKP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/RuckertM0N14, author = {Elmar Rueckert and Max Mindt and Jan Peters and Gerhard Neumann}, title = {Robust policy updates for stochastic optimal control}, booktitle = {14th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014}, pages = {388--393}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/HUMANOIDS.2014.7041389}, doi = {10.1109/HUMANOIDS.2014.7041389}, timestamp = {Wed, 02 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/RuckertM0N14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/MaedaELA0N14, author = {Guilherme Maeda and Marco Ewerton and Rudolf Lioutikov and Heni Ben Amor and Jan Peters and Gerhard Neumann}, title = {Learning interaction for collaborative tasks with probabilistic movement primitives}, booktitle = {14th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014}, pages = {527--534}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/HUMANOIDS.2014.7041413}, doi = {10.1109/HUMANOIDS.2014.7041413}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/MaedaELA0N14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/BrandiK014, author = {Sascha Brandi and Oliver Kroemer and Jan Peters}, title = {Generalizing pouring actions between objects using warped parameters}, booktitle = {14th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014}, pages = {616--621}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/HUMANOIDS.2014.7041426}, doi = {10.1109/HUMANOIDS.2014.7041426}, timestamp = {Wed, 17 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/BrandiK014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/ColomeN0T14, author = {Adria Colome and Gerhard Neumann and Jan Peters and Carme Torras}, title = {Dimensionality reduction for probabilistic movement primitives}, booktitle = {14th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014}, pages = {794--800}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/HUMANOIDS.2014.7041454}, doi = {10.1109/HUMANOIDS.2014.7041454}, timestamp = {Mon, 26 Jun 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/ColomeN0T14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/Ivaldi0PN14, author = {Serena Ivaldi and Jan Peters and Vincent Padois and Francesco Nori}, title = {Tools for simulating humanoid robot dynamics: {A} survey based on user feedback}, booktitle = {14th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2014, Madrid, Spain, November 18-20, 2014}, pages = {842--849}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/HUMANOIDS.2014.7041462}, doi = {10.1109/HUMANOIDS.2014.7041462}, timestamp = {Mon, 06 Nov 2017 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/Ivaldi0PN14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ias/LioutikovKM014, author = {Rudolf Lioutikov and Oliver Kroemer and Guilherme Maeda and Jan Peters}, editor = {Emanuele Menegatti and Nathan Michael and Karsten Berns and Hiroaki Yamaguchi}, title = {Learning Manipulation by Sequencing Motor Primitives with a Two-Armed Robot}, booktitle = {Intelligent Autonomous Systems 13 - Proceedings of the 13th International Conference IAS-13, Padova, Italy, July 15-18, 2014}, series = {Advances in Intelligent Systems and Computing}, volume = {302}, pages = {1601--1611}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-08338-4\_115}, doi = {10.1007/978-3-319-08338-4\_115}, timestamp = {Tue, 23 May 2017 01:06:19 +0200}, biburl = {https://dblp.org/rec/conf/ias/LioutikovKM014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iberamia/AbdolmalekiSRLPN14, author = {Abbas Abdolmaleki and Nima Shafii and Lu{\'{\i}}s Paulo Reis and Nuno Lau and Jan Peters and Gerhard Neumann}, editor = {Ana L. C. Bazzan and Karim Pichara}, title = {Omnidirectional Walking with a Compliant Inverted Pendulum Model}, booktitle = {Advances in Artificial Intelligence - {IBERAMIA} 2014 - 14th Ibero-American Conference on AI, Santiago de Chile, Chile, November 24-27, 2014, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {8864}, pages = {481--493}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-12027-0\_39}, doi = {10.1007/978-3-319-12027-0\_39}, timestamp = {Sun, 02 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iberamia/AbdolmalekiSRLPN14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icassp/KamthePD14, author = {Sanket Kamthe and Jan Peters and Marc Peter Deisenroth}, title = {Multi-modal filtering for non-linear estimation}, booktitle = {{IEEE} International Conference on Acoustics, Speech and Signal Processing, {ICASSP} 2014, Florence, Italy, May 4-9, 2014}, pages = {7979--7983}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICASSP.2014.6855154}, doi = {10.1109/ICASSP.2014.6855154}, timestamp = {Wed, 16 Oct 2019 14:14:52 +0200}, biburl = {https://dblp.org/rec/conf/icassp/KamthePD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/CalandraSPD14, author = {Roberto Calandra and Andr{\'{e}} Seyfarth and Jan Peters and Marc Peter Deisenroth}, title = {An experimental comparison of Bayesian optimization for bipedal locomotion}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {1951--1958}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907117}, doi = {10.1109/ICRA.2014.6907117}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/CalandraSPD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/AmorNKKP14, author = {Heni Ben Amor and Gerhard Neumann and Sanket Kamthe and Oliver Kroemer and Jan Peters}, title = {Interaction primitives for human-robot cooperation tasks}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {2831--2837}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907265}, doi = {10.1109/ICRA.2014.6907265}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/AmorNKKP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/DeisenrothEPF14, author = {Marc Peter Deisenroth and Peter Englert and Jan Peters and Dieter Fox}, title = {Multi-task policy search for robotics}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {3876--3881}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907421}, doi = {10.1109/ICRA.2014.6907421}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/DeisenrothEPF14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/BischoffNHMRKPD14, author = {Bastian Bischoff and Duy Nguyen{-}Tuong and Herke van Hoof and Andrew McHutchon and Carl E. Rasmussen and Alois C. Knoll and Jan Peters and Marc Peter Deisenroth}, title = {Policy search for learning robot control using sparse data}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {3882--3887}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907422}, doi = {10.1109/ICRA.2014.6907422}, timestamp = {Wed, 19 May 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/BischoffNHMRKPD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LioutikovPPN14, author = {Rudolf Lioutikov and Alexandros Paraschos and Jan Peters and Gerhard Neumann}, title = {Sample-based informationl-theoretic stochastic optimal control}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {3896--3902}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907424}, doi = {10.1109/ICRA.2014.6907424}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/LioutikovPPN14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KroemerHNP14, author = {Oliver Kroemer and Herke van Hoof and Gerhard Neumann and Jan Peters}, title = {Learning to predict phases of manipulation tasks as hidden states}, booktitle = {2014 {IEEE} International Conference on Robotics and Automation, {ICRA} 2014, Hong Kong, China, May 31 - June 7, 2014}, pages = {4009--4014}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/ICRA.2014.6907441}, doi = {10.1109/ICRA.2014.6907441}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/KroemerHNP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/LuckNBPA14, author = {Kevin Sebastian Luck and Gerhard Neumann and Erik Berger and Jan Peters and Heni Ben Amor}, title = {Latent space policy search for robotics}, booktitle = {2014 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2014, Chicago, IL, USA, September 14-18, 2014}, pages = {1434--1440}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/IROS.2014.6942745}, doi = {10.1109/IROS.2014.6942745}, timestamp = {Tue, 05 Sep 2023 15:07:47 +0200}, biburl = {https://dblp.org/rec/conf/iros/LuckNBPA14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KroemerP14, author = {Oliver Kroemer and Jan Peters}, title = {Predicting object interactions from contact distributions}, booktitle = {2014 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2014, Chicago, IL, USA, September 14-18, 2014}, pages = {3361--3367}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/IROS.2014.6943030}, doi = {10.1109/IROS.2014.6943030}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/KroemerP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ChebotarKP14, author = {Yevgen Chebotar and Oliver Kroemer and Jan Peters}, title = {Learning robot tactile sensing for object manipulation}, booktitle = {2014 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2014, Chicago, IL, USA, September 14-18, 2014}, pages = {3368--3375}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/IROS.2014.6943031}, doi = {10.1109/IROS.2014.6943031}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/ChebotarKP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ManschitzKGP14, author = {Simon Manschitz and Jens Kober and Michael Gienger and Jan Peters}, title = {Learning to sequence movement primitives from demonstrations}, booktitle = {2014 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2014, Chicago, IL, USA, September 14-18, 2014}, pages = {4414--4421}, publisher = {{IEEE}}, year = {2014}, url = {https://doi.org/10.1109/IROS.2014.6943187}, doi = {10.1109/IROS.2014.6943187}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/ManschitzKGP14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/lion/CalandraGSPD14, author = {Roberto Calandra and Nakul Gopalan and Andr{\'{e}} Seyfarth and Jan Peters and Marc Peter Deisenroth}, editor = {Panos M. Pardalos and Mauricio G. C. Resende and Chrysafis Vogiatzis and Jose L. Walteros}, title = {Bayesian Gait Optimization for Bipedal Locomotion}, booktitle = {Learning and Intelligent Optimization - 8th International Conference, Lion 8, Gainesville, FL, USA, February 16-21, 2014. Revised Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {8426}, pages = {274--290}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-319-09584-4\_25}, doi = {10.1007/978-3-319-09584-4\_25}, timestamp = {Tue, 14 May 2019 10:00:51 +0200}, biburl = {https://dblp.org/rec/conf/lion/CalandraGSPD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/GomezKPN14, author = {Vicen{\c{c}} G{\'{o}}mez and Hilbert J. Kappen and Jan Peters and Gerhard Neumann}, editor = {Toon Calders and Floriana Esposito and Eyke H{\"{u}}llermeier and Rosa Meo}, title = {Policy Search for Path Integral Control}, booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, {ECML} {PKDD} 2014, Nancy, France, September 15-19, 2014. Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {8724}, pages = {482--497}, publisher = {Springer}, year = {2014}, url = {https://doi.org/10.1007/978-3-662-44848-9\_31}, doi = {10.1007/978-3-662-44848-9\_31}, timestamp = {Thu, 31 Oct 2019 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/pkdd/GomezKPN14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/DanielVMK014, author = {Christian Daniel and Malte Viering and Jan Metz and Oliver Kroemer and Jan Peters}, editor = {Dieter Fox and Lydia E. Kavraki and Hanna Kurniawati}, title = {Active Reward Learning}, booktitle = {Robotics: Science and Systems X, University of California, Berkeley, USA, July 12-16, 2014}, year = {2014}, url = {http://www.roboticsproceedings.org/rss10/p31.html}, doi = {10.15607/RSS.2014.X.031}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/rss/DanielVMK014.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/KamthePD14, author = {Sanket Kamthe and Jan Peters and Marc Peter Deisenroth}, title = {Multi-modal filtering for non-linear estimation}, journal = {CoRR}, volume = {abs/1401.0077}, year = {2014}, url = {http://arxiv.org/abs/1401.0077}, eprinttype = {arXiv}, eprint = {1401.0077}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/KamthePD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/CalandraPRD14, author = {Roberto Calandra and Jan Peters and Carl Edward Rasmussen and Marc Peter Deisenroth}, title = {Manifold Gaussian Processes for Regression}, journal = {CoRR}, volume = {abs/1402.5876}, year = {2014}, url = {http://arxiv.org/abs/1402.5876}, eprinttype = {arXiv}, eprint = {1402.5876}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/CalandraPRD14.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/adb/EnglertPDP13, author = {Peter Englert and Alexandros Paraschos and Marc Peter Deisenroth and Jan Peters}, title = {Probabilistic model-based imitation learning}, journal = {Adapt. Behav.}, volume = {21}, number = {5}, pages = {388--403}, year = {2013}, url = {https://doi.org/10.1177/1059712313491614}, doi = {10.1177/1059712313491614}, timestamp = {Tue, 25 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/adb/EnglertPDP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ftrob/DeisenrothNP13, author = {Marc Peter Deisenroth and Gerhard Neumann and Jan Peters}, title = {A Survey on Policy Search for Robotics}, journal = {Found. Trends Robotics}, volume = {2}, number = {1-2}, pages = {1--142}, year = {2013}, url = {https://doi.org/10.1561/2300000021}, doi = {10.1561/2300000021}, timestamp = {Thu, 10 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ftrob/DeisenrothNP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/MullingKKP13, author = {Katharina M{\"{u}}lling and Jens Kober and Oliver Kroemer and Jan Peters}, title = {Learning to select and generalize striking movements in robot table tennis}, journal = {Int. J. Robotics Res.}, volume = {32}, number = {3}, pages = {263--279}, year = {2013}, url = {https://doi.org/10.1177/0278364912472380}, doi = {10.1177/0278364912472380}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/MullingKKP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/WangMDAVSP13, author = {Zhikun Wang and Katharina M{\"{u}}lling and Marc Peter Deisenroth and Heni Ben Amor and David Vogt and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Probabilistic movement modeling for intention inference in human-robot interaction}, journal = {Int. J. Robotics Res.}, volume = {32}, number = {7}, pages = {841--858}, year = {2013}, url = {https://doi.org/10.1177/0278364913478447}, doi = {10.1177/0278364913478447}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/WangMDAVSP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/KoberBP13, author = {Jens Kober and J. Andrew Bagnell and Jan Peters}, title = {Reinforcement learning in robotics: {A} survey}, journal = {Int. J. Robotics Res.}, volume = {32}, number = {11}, pages = {1238--1274}, year = {2013}, url = {https://doi.org/10.1177/0278364913495721}, doi = {10.1177/0278364913495721}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/KoberBP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/KupcsikDPN13, author = {Andras Gabor Kupcsik and Marc Peter Deisenroth and Jan Peters and Gerhard Neumann}, editor = {Marie desJardins and Michael L. Littman}, title = {Data-Efficient Generalization of Robot Skills with Contextual Policy Search}, booktitle = {Proceedings of the Twenty-Seventh {AAAI} Conference on Artificial Intelligence, July 14-18, 2013, Bellevue, Washington, {USA}}, pages = {1401--1407}, publisher = {{AAAI} Press}, year = {2013}, url = {https://doi.org/10.1609/aaai.v27i1.8546}, doi = {10.1609/AAAI.V27I1.8546}, timestamp = {Sat, 21 Oct 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/KupcsikDPN13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/HoofK013, author = {Herke van Hoof and Oliver Kroemer and Jan Peters}, title = {Probabilistic interactive segmentation for anthropomorphic robots in cluttered environments}, booktitle = {13th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2013, Atlanta, GA, USA, October 15-17, 2013}, pages = {169--176}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/HUMANOIDS.2013.7029972}, doi = {10.1109/HUMANOIDS.2013.7029972}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/HoofK013.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/ParaschosN013, author = {Alexandros Paraschos and Gerhard Neumann and Jan Peters}, title = {A probabilistic approach to robot trajectory generation}, booktitle = {13th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2013, Atlanta, GA, USA, October 15-17, 2013}, pages = {477--483}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/HUMANOIDS.2013.7030017}, doi = {10.1109/HUMANOIDS.2013.7030017}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/humanoids/ParaschosN013.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/GopalanDP13, author = {Nakul Gopalan and Marc Peter Deisenroth and Jan Peters}, title = {Feedback error learning for rhythmic motor primitives}, booktitle = {2013 {IEEE} International Conference on Robotics and Automation, Karlsruhe, Germany, May 6-10, 2013}, pages = {1317--1322}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICRA.2013.6630741}, doi = {10.1109/ICRA.2013.6630741}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/GopalanDP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/EnglertPPD13, author = {Peter Englert and Alexandros Paraschos and Jan Peters and Marc Peter Deisenroth}, title = {Model-based imitation learning by probabilistic trajectory matching}, booktitle = {2013 {IEEE} International Conference on Robotics and Automation, Karlsruhe, Germany, May 6-10, 2013}, pages = {1922--1927}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICRA.2013.6630832}, doi = {10.1109/ICRA.2013.6630832}, timestamp = {Sun, 02 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/EnglertPPD13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/DanielNKP13, author = {Christian Daniel and Gerhard Neumann and Oliver Kroemer and Jan Peters}, title = {Learning sequential motor tasks}, booktitle = {2013 {IEEE} International Conference on Robotics and Automation, Karlsruhe, Germany, May 6-10, 2013}, pages = {2626--2632}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/ICRA.2013.6630937}, doi = {10.1109/ICRA.2013.6630937}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/DanielNKP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/BocsiCP13, author = {Botond Bocsi and Lehel Csat{\'{o}} and Jan Peters}, title = {Alignment-based transfer learning for robot models}, booktitle = {The 2013 International Joint Conference on Neural Networks, {IJCNN} 2013, Dallas, TX, USA, August 4-9, 2013}, pages = {1--7}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/IJCNN.2013.6706721}, doi = {10.1109/IJCNN.2013.6706721}, timestamp = {Wed, 16 Oct 2019 14:14:55 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/BocsiCP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/DanielNP13, author = {Christian Daniel and Gerhard Neumann and Jan Peters}, title = {Autonomous reinforcement learning with hierarchical {REPS}}, booktitle = {The 2013 International Joint Conference on Neural Networks, {IJCNN} 2013, Dallas, TX, USA, August 4-9, 2013}, pages = {1--8}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/IJCNN.2013.6706759}, doi = {10.1109/IJCNN.2013.6706759}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/ijcnn/DanielNP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/AmorVEBJP13, author = {Heni Ben Amor and David Vogt and Marco Ewerton and Erik Berger and Bernhard Jung and Jan Peters}, title = {Learning responsive robot behavior by imitation}, booktitle = {2013 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2013, Tokyo, Japan, November 3-7, 2013}, pages = {3257--3264}, publisher = {{IEEE}}, year = {2013}, url = {https://doi.org/10.1109/IROS.2013.6696819}, doi = {10.1109/IROS.2013.6696819}, timestamp = {Tue, 05 Sep 2023 15:06:24 +0200}, biburl = {https://dblp.org/rec/conf/iros/AmorVEBJP13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/ParaschosDPN13, author = {Alexandros Paraschos and Christian Daniel and Jan Peters and Gerhard Neumann}, editor = {Christopher J. C. Burges and L{\'{e}}on Bottou and Zoubin Ghahramani and Kilian Q. Weinberger}, title = {Probabilistic Movement Primitives}, booktitle = {Advances in Neural Information Processing Systems 26: 27th Annual Conference on Neural Information Processing Systems 2013. Proceedings of a meeting held December 5-8, 2013, Lake Tahoe, Nevada, United States}, pages = {2616--2624}, year = {2013}, url = {https://proceedings.neurips.cc/paper/2013/hash/e53a0a2978c28872a4505bdb51db06dc-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/ParaschosDPN13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/PetersKMKN13, author = {Jan Peters and Jens Kober and Katharina M{\"{u}}lling and Oliver Kr{\"{o}}mer and Gerhard Neumann}, editor = {Hendrik Blockeel and Kristian Kersting and Siegfried Nijssen and Filip Zelezn{\'{y}}}, title = {Towards Robot Skill Learning: From Simple Skills to Table Tennis}, booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, {ECML} {PKDD} 2013, Prague, Czech Republic, September 23-27, 2013, Proceedings, Part {III}}, series = {Lecture Notes in Computer Science}, volume = {8190}, pages = {627--631}, publisher = {Springer}, year = {2013}, url = {https://doi.org/10.1007/978-3-642-40994-3\_42}, doi = {10.1007/978-3-642-40994-3\_42}, timestamp = {Tue, 21 Mar 2023 21:00:11 +0100}, biburl = {https://dblp.org/rec/conf/pkdd/PetersKMKN13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/DeisenrothEPF13, author = {Marc Peter Deisenroth and Peter Englert and Jan Peters and Dieter Fox}, title = {Multi-Task Policy Search}, journal = {CoRR}, volume = {abs/1307.0813}, year = {2013}, url = {http://arxiv.org/abs/1307.0813}, eprinttype = {arXiv}, eprint = {1307.0813}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/DeisenrothEPF13.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/KoberWOP12, author = {Jens Kober and Andreas Wilhelm and Erhan {\"{O}}ztop and Jan Peters}, title = {Reinforcement learning to adjust parametrized motor primitives to new situations}, journal = {Auton. Robots}, volume = {33}, number = {4}, pages = {361--379}, year = {2012}, url = {https://doi.org/10.1007/s10514-012-9290-3}, doi = {10.1007/S10514-012-9290-3}, timestamp = {Mon, 16 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/KoberWOP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijicc/GaoPT12, author = {Yang Gao and Jan Peters and Antonios Tsourdos}, title = {Special issue on "Bio-inspired computing for autonomous vehicles"}, journal = {Int. J. Intell. Comput. Cybern.}, volume = {5}, number = {3}, year = {2012}, url = {https://doi.org/10.1108/ijicc.2012.39805caa.001}, doi = {10.1108/IJICC.2012.39805CAA.001}, timestamp = {Sun, 06 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijicc/GaoPT12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/jrtip/LampertP12, author = {Christoph H. Lampert and Jan Peters}, title = {Real-time detection of colored objects in multiple camera streams with off-the-shelf hardware components}, journal = {J. Real Time Image Process.}, volume = {7}, number = {1}, pages = {31--41}, year = {2012}, url = {https://doi.org/10.1007/s11554-010-0168-3}, doi = {10.1007/S11554-010-0168-3}, timestamp = {Thu, 18 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/jrtip/LampertP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/tnn/Nguyen-TuongP12, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Online Kernel-Based Learning for Task-Space Tracking Robot Control}, journal = {{IEEE} Trans. Neural Networks Learn. Syst.}, volume = {23}, number = {9}, pages = {1417--1425}, year = {2012}, url = {https://doi.org/10.1109/TNNLS.2012.2201261}, doi = {10.1109/TNNLS.2012.2201261}, timestamp = {Mon, 09 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/tnn/Nguyen-TuongP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaaifs/MullingKKP12, author = {Katharina M{\"{u}}lling and Jens Kober and Oliver Kroemer and Jan Peters}, title = {Learning to Select and Generalize Striking Movements in Robot Table Tennis}, booktitle = {Robots Learning Interactively from Human Teachers, Papers from the 2012 {AAAI} Fall Symposium, Arlington, Virginia, USA, November 2-4, 2012}, series = {{AAAI} Technical Report}, volume = {{FS-12-07}}, publisher = {{AAAI}}, year = {2012}, url = {http://www.aaai.org/ocs/index.php/FSS/FSS12/paper/view/5602}, timestamp = {Tue, 08 Mar 2022 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/aaaifs/MullingKKP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ecai/PetersMKNK12, author = {Jan Peters and Katharina M{\"{u}}lling and Jens Kober and Duy Nguyen{-}Tuong and Oliver Kr{\"{o}}mer}, editor = {Luc De Raedt and Christian Bessiere and Didier Dubois and Patrick Doherty and Paolo Frasconi and Fredrik Heintz and Peter J. F. Lucas}, title = {Robot Skill Learning}, booktitle = {{ECAI} 2012 - 20th European Conference on Artificial Intelligence. Including Prestigious Applications of Artificial Intelligence {(PAIS-2012)} System Demonstrations Track, Montpellier, France, August 27-31 , 2012}, series = {Frontiers in Artificial Intelligence and Applications}, volume = {242}, pages = {40--45}, publisher = {{IOS} Press}, year = {2012}, url = {https://doi.org/10.3233/978-1-61499-098-7-40}, doi = {10.3233/978-1-61499-098-7-40}, timestamp = {Mon, 19 Jun 2023 16:36:09 +0200}, biburl = {https://dblp.org/rec/conf/ecai/PetersMKNK12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ewrl/DeisenrothSP12, author = {Marc Peter Deisenroth and Csaba Szepesv{\'{a}}ri and Jan Peters}, editor = {Marc Peter Deisenroth and Csaba Szepesv{\'{a}}ri and Jan Peters}, title = {Preface}, booktitle = {Proceedings of the Tenth European Workshop on Reinforcement Learning, {EWRL} 2012, Edinburgh, Scotland, UK, June, 2012}, series = {{JMLR} Proceedings}, volume = {24}, publisher = {JMLR.org}, year = {2012}, url = {http://proceedings.mlr.press/v24/deisenroth12a/deisenroth12a.pdf}, timestamp = {Wed, 29 May 2019 08:41:44 +0200}, biburl = {https://dblp.org/rec/conf/ewrl/DeisenrothSP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/KroemerAEP12, author = {Oliver Kroemer and Heni Ben Amor and Marco Ewerton and Jan Peters}, title = {Point cloud completion using extrusions}, booktitle = {12th {IEEE-RAS} International Conference on Humanoid Robots (Humanoids 2012), Osaka, Japan, November 29 - Dec. 1, 2012}, pages = {680--685}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/HUMANOIDS.2012.6651593}, doi = {10.1109/HUMANOIDS.2012.6651593}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/KroemerAEP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/BocsiHCP12, author = {Botond Bocsi and Philipp Hennig and Lehel Csat{\'{o}} and Jan Peters}, title = {Learning tracking control with forward models}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2012, 14-18 May, 2012, St. Paul, Minnesota, {USA}}, pages = {259--264}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICRA.2012.6224831}, doi = {10.1109/ICRA.2012.6224831}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/icra/BocsiHCP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KroemerUOP12, author = {Oliver Kroemer and Emre Ugur and Erhan {\"{O}}ztop and Jan Peters}, title = {A kernel-based approach to direct action perception}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2012, 14-18 May, 2012, St. Paul, Minnesota, {USA}}, pages = {2605--2610}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/ICRA.2012.6224957}, doi = {10.1109/ICRA.2012.6224957}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/KroemerUOP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/DeisenrothCSP12, author = {Marc Peter Deisenroth and Roberto Calandra and Andr{\'{e}} Seyfarth and Jan Peters}, title = {Toward fast policy search for learning legged locomotion}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {1787--1792}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6385955}, doi = {10.1109/IROS.2012.6385955}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/DeisenrothCSP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/AmorKHNP12, author = {Heni Ben Amor and Oliver Kroemer and Ulrich Hillenbrand and Gerhard Neumann and Jan Peters}, title = {Generalization of human grasping for multi-fingered robot hands}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {2043--2050}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6386072}, doi = {10.1109/IROS.2012.6386072}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/AmorKHNP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/DanielNP12, author = {Christian Daniel and Gerhard Neumann and Jan Peters}, title = {Learning concurrent motor skills in versatile solution spaces}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {3591--3597}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6386047}, doi = {10.1109/IROS.2012.6386047}, timestamp = {Fri, 02 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/DanielNP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/MeyerPBZSSG12, author = {Timm Meyer and Jan Peters and Doris Brtz and Thorsten O. Zander and Bernhard Sch{\"{o}}lkopf and Surjo R. Soekadar and Moritz Grosse{-}Wentrup}, title = {A brain-robot interface for studying motor learning after stroke}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {4078--4083}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6385646}, doi = {10.1109/IROS.2012.6385646}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/MeyerPBZSSG12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/HoofKAP12, author = {Herke van Hoof and Oliver Kroemer and Heni Ben Amor and Jan Peters}, title = {Maximally informative interaction learning for scene exploration}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {5152--5158}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6386008}, doi = {10.1109/IROS.2012.6386008}, timestamp = {Thu, 15 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/HoofKAP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KoberMP12, author = {Jens Kober and Katharina M{\"{u}}lling and Jan Peters}, title = {Learning throwing and catching skills}, booktitle = {2012 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2012, Vilamoura, Algarve, Portugal, October 7-12, 2012}, pages = {5167--5168}, publisher = {{IEEE}}, year = {2012}, url = {https://doi.org/10.1109/IROS.2012.6386267}, doi = {10.1109/IROS.2012.6386267}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/KoberMP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/BoulariasKP12, author = {Abdeslam Boularias and Oliver Kroemer and Jan Peters}, editor = {Peter L. Bartlett and Fernando C. N. Pereira and Christopher J. C. Burges and L{\'{e}}on Bottou and Kilian Q. Weinberger}, title = {Algorithms for Learning Markov Field Policies}, booktitle = {Advances in Neural Information Processing Systems 25: 26th Annual Conference on Neural Information Processing Systems 2012. Proceedings of a meeting held December 3-6, 2012, Lake Tahoe, Nevada, United States}, pages = {2186--2194}, year = {2012}, url = {https://proceedings.neurips.cc/paper/2012/hash/9f36407ead0629fc166f14dde7970f68-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/BoulariasKP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/BoulariasKP12, author = {Abdeslam Boularias and Oliver Kr{\"{o}}mer and Jan Peters}, editor = {Peter A. Flach and Tijl De Bie and Nello Cristianini}, title = {Structured Apprenticeship Learning}, booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference, {ECML} {PKDD} 2012, Bristol, UK, September 24-28, 2012. Proceedings, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {7524}, pages = {227--242}, publisher = {Springer}, year = {2012}, url = {https://doi.org/10.1007/978-3-642-33486-3\_15}, doi = {10.1007/978-3-642-33486-3\_15}, timestamp = {Tue, 14 May 2019 10:00:47 +0200}, biburl = {https://dblp.org/rec/conf/pkdd/BoulariasKP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/WangDAVSP12, author = {Zhikun Wang and Marc Peter Deisenroth and Heni Ben Amor and David Vogt and Bernhard Sch{\"{o}}lkopf and Jan Peters}, editor = {Nicholas Roy and Paul Newman and Siddhartha S. Srinivasa}, title = {Probabilistic Modeling of Human Movements for Intention Inference}, booktitle = {Robotics: Science and Systems VIII, University of Sydney, Sydney, NSW, Australia, July 9-13, 2012}, year = {2012}, url = {http://www.roboticsproceedings.org/rss08/p55.html}, doi = {10.15607/RSS.2012.VIII.055}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/rss/WangDAVSP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:journals/jmlr/DanielNP12, author = {Christian Daniel and Gerhard Neumann and Jan Peters}, editor = {Neil D. Lawrence and Mark A. Girolami}, title = {Hierarchical Relative Entropy Policy Search}, booktitle = {Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2012, La Palma, Canary Islands, Spain, April 21-23, 2012}, series = {{JMLR} Proceedings}, volume = {22}, pages = {273--281}, publisher = {JMLR.org}, year = {2012}, url = {http://proceedings.mlr.press/v22/daniel12.html}, timestamp = {Wed, 29 May 2019 08:41:44 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/DanielNP12.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:books/sp/12/Kober012, author = {Jens Kober and Jan Peters}, editor = {Marco A. Wiering and Martijn van Otterlo}, title = {Reinforcement Learning in Robotics: {A} Survey}, booktitle = {Reinforcement Learning}, series = {Adaptation, Learning, and Optimization}, volume = {12}, pages = {579--610}, publisher = {Springer}, year = {2012}, url = {https://doi.org/10.1007/978-3-642-27645-3\_18}, doi = {10.1007/978-3-642-27645-3\_18}, timestamp = {Tue, 29 Dec 2020 18:14:51 +0100}, biburl = {https://dblp.org/rec/books/sp/12/Kober012.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/ewrl/2012, editor = {Marc Peter Deisenroth and Csaba Szepesv{\'{a}}ri and Jan Peters}, title = {Proceedings of the Tenth European Workshop on Reinforcement Learning, {EWRL} 2012, Edinburgh, Scotland, UK, June, 2012}, series = {{JMLR} Proceedings}, volume = {24}, publisher = {JMLR.org}, year = {2012}, url = {http://proceedings.mlr.press/v24/}, timestamp = {Wed, 29 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ewrl/2012.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1209-0488, author = {Jens Kober and Jan Peters}, title = {Learning Prioritized Control of Motor Primitives}, journal = {CoRR}, volume = {abs/1209.0488}, year = {2012}, url = {http://arxiv.org/abs/1209.0488}, eprinttype = {arXiv}, eprint = {1209.0488}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1209-0488.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/adb/MullingKP11, author = {Katharina M{\"{u}}lling and Jens Kober and Jan Peters}, title = {A biomimetic approach to robot table tennis}, journal = {Adapt. Behav.}, volume = {19}, number = {5}, pages = {359--376}, year = {2011}, url = {https://doi.org/10.1177/1059712311419378}, doi = {10.1177/1059712311419378}, timestamp = {Tue, 25 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/adb/MullingKP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cp/Nguyen-TuongP11, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Model learning for robot control: a survey}, journal = {Cogn. Process.}, volume = {12}, number = {4}, pages = {319--340}, year = {2011}, url = {https://doi.org/10.1007/s10339-011-0404-1}, doi = {10.1007/S10339-011-0404-1}, timestamp = {Thu, 04 Jun 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/cp/Nguyen-TuongP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijon/Nguyen-TuongP11, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Incremental online sparsification for model learning in real-time robot control}, journal = {Neurocomputing}, volume = {74}, number = {11}, pages = {1859--1867}, year = {2011}, url = {https://doi.org/10.1016/j.neucom.2010.06.033}, doi = {10.1016/J.NEUCOM.2010.06.033}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ijon/Nguyen-TuongP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/PiaterJDKKKP11, author = {Justus H. Piater and S{\'{e}}bastien Jodogne and Renaud Detry and Dirk Kraft and Norbert Kr{\"{u}}ger and Oliver Kroemer and Jan Peters}, title = {Learning visual representations for perception-action systems}, journal = {Int. J. Robotics Res.}, volume = {30}, number = {3}, pages = {294--307}, year = {2011}, url = {https://doi.org/10.1177/0278364910382464}, doi = {10.1177/0278364910382464}, timestamp = {Sun, 06 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/PiaterJDKKKP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ml/KoberP11, author = {Jens Kober and Jan Peters}, title = {Policy search for motor primitives in robotics}, journal = {Mach. Learn.}, volume = {84}, number = {1-2}, pages = {171--203}, year = {2011}, url = {https://doi.org/10.1007/s10994-010-5223-6}, doi = {10.1007/S10994-010-5223-6}, timestamp = {Mon, 02 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ml/KoberP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/neco/HachiyaPS11, author = {Hirotaka Hachiya and Jan Peters and Masashi Sugiyama}, title = {Reward-Weighted Regression with Sample Reuse for Direct Policy Search in Reinforcement Learning}, journal = {Neural Comput.}, volume = {23}, number = {11}, pages = {2798--2832}, year = {2011}, url = {https://doi.org/10.1162/NECO\_a\_00199}, doi = {10.1162/NECO\_A\_00199}, timestamp = {Tue, 01 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/neco/HachiyaPS11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/paladyn/DetryKKBPKP11, author = {Renaud Detry and Dirk Kraft and Oliver Kroemer and Leon Bodenhagen and Jan Peters and Norbert Kr{\"{u}}ger and Justus H. Piater}, title = {Learning grasp affordance densities}, journal = {Paladyn J. Behav. Robotics}, volume = {2}, number = {1}, pages = {1--17}, year = {2011}, url = {https://doi.org/10.2478/s13230-011-0012-x}, doi = {10.2478/S13230-011-0012-X}, timestamp = {Fri, 07 Aug 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/paladyn/DetryKKBPKP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/trob/KroemerLP11, author = {Oliver Kroemer and Christoph H. Lampert and Jan Peters}, title = {Learning Dynamic Tactile Sensing With Robust Vision-Based Training}, journal = {{IEEE} Trans. Robotics}, volume = {27}, number = {3}, pages = {545--557}, year = {2011}, url = {https://doi.org/10.1109/TRO.2011.2121130}, doi = {10.1109/TRO.2011.2121130}, timestamp = {Fri, 09 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/trob/KroemerLP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/WangBMP11, author = {Zhikun Wang and Abdeslam Boularias and Katharina M{\"{u}}lling and Jan Peters}, editor = {Wolfram Burgard and Dan Roth}, title = {Balancing Safety and Exploitability in Opponent Modeling}, booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2011, San Francisco, California, USA, August 7-11, 2011}, pages = {1515--1520}, publisher = {{AAAI} Press}, year = {2011}, url = {https://doi.org/10.1609/aaai.v25i1.7981}, doi = {10.1609/AAAI.V25I1.7981}, timestamp = {Mon, 04 Sep 2023 16:05:54 +0200}, biburl = {https://dblp.org/rec/conf/aaai/WangBMP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/WangBMP11a, author = {Zhikun Wang and Abdeslam Boularias and Katharina M{\"{u}}lling and Jan Peters}, editor = {Wolfram Burgard and Dan Roth}, title = {Modeling Opponent Actions for Table-Tennis Playing Robot}, booktitle = {Proceedings of the Twenty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI} 2011, San Francisco, California, USA, August 7-11, 2011}, pages = {1828--1829}, publisher = {{AAAI} Press}, year = {2011}, url = {https://doi.org/10.1609/aaai.v25i1.8051}, doi = {10.1609/AAAI.V25I1.8051}, timestamp = {Mon, 04 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/WangBMP11a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/adprl/KroemerP11, author = {Oliver Kroemer and Jan Peters}, title = {Active exploration for robot parameter selection in episodic reinforcement learning}, booktitle = {2011 {IEEE} Symposium on Adaptive Dynamic Programming And Reinforcement Learning, {ADPRL} 2011, Paris, France, April 12-14, 2011}, pages = {25--31}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ADPRL.2011.5967378}, doi = {10.1109/ADPRL.2011.5967378}, timestamp = {Wed, 16 Oct 2019 14:14:48 +0200}, biburl = {https://dblp.org/rec/conf/adprl/KroemerP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KroemerP11, author = {Oliver Kroemer and Jan Peters}, title = {A flexible hybrid framework for modeling complex manipulation tasks}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2011, Shanghai, China, 9-13 May 2011}, pages = {1856--1861}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ICRA.2011.5980237}, doi = {10.1109/ICRA.2011.5980237}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/KroemerP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/LamparielloNCHP11, author = {Roberto Lampariello and Duy Nguyen{-}Tuong and Claudio Castellini and Gerd Hirzinger and Jan Peters}, title = {Trajectory planning for optimal robot catching in real-time}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2011, Shanghai, China, 9-13 May 2011}, pages = {3719--3726}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/ICRA.2011.5980114}, doi = {10.1109/ICRA.2011.5980114}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/LamparielloNCHP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcai/KoberOP11, author = {Jens Kober and Erhan {\"{O}}ztop and Jan Peters}, editor = {Toby Walsh}, title = {Reinforcement Learning to Adjust Robot Movements to New Situations}, booktitle = {{IJCAI} 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, Spain, July 16-22, 2011}, pages = {2650--2655}, publisher = {{IJCAI/AAAI}}, year = {2011}, url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-441}, doi = {10.5591/978-1-57735-516-8/IJCAI11-441}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ijcai/KoberOP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/WangLMSP11, author = {Zhikun Wang and Christoph H. Lampert and Katharina M{\"{u}}lling and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning anticipation policies for robot table tennis}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {332--337}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094892}, doi = {10.1109/IROS.2011.6094892}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/WangLMSP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KoberP11, author = {Jens Kober and Jan Peters}, title = {Learning elementary movements jointly with a higher level task}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {338--343}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094834}, doi = {10.1109/IROS.2011.6094834}, timestamp = {Mon, 16 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/KoberP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/BocsiNCSP11, author = {Botond Bocsi and Duy Nguyen{-}Tuong and Lehel Csat{\'{o}} and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Learning inverse kinematics with structured prediction}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {698--703}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094666}, doi = {10.1109/IROS.2011.6094666}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/BocsiNCSP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Nguyen-TuongP11, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Learning task-space tracking control with kernels}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {704--709}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094428}, doi = {10.1109/IROS.2011.6094428}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/Nguyen-TuongP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/BoulariasKP11, author = {Abdeslam Boularias and Oliver Kroemer and Jan Peters}, title = {Learning robot grasping from 3-D images with Markov Random Fields}, booktitle = {2011 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2011, San Francisco, CA, USA, September 25-30, 2011}, pages = {1548--1553}, publisher = {{IEEE}}, year = {2011}, url = {https://doi.org/10.1109/IROS.2011.6094888}, doi = {10.1109/IROS.2011.6094888}, timestamp = {Mon, 22 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/BoulariasKP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KroemerP11, author = {Oliver Kroemer and Jan Peters}, editor = {John Shawe{-}Taylor and Richard S. Zemel and Peter L. Bartlett and Fernando C. N. Pereira and Kilian Q. Weinberger}, title = {A Non-Parametric Approach to Dynamic Programming}, booktitle = {Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011. Proceedings of a meeting held 12-14 December 2011, Granada, Spain}, pages = {1719--1727}, year = {2011}, url = {https://proceedings.neurips.cc/paper/2011/hash/4311359ed4969e8401880e3c1836fbe1-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/KroemerP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:journals/jmlr/BoulariasKP11, author = {Abdeslam Boularias and Jens Kober and Jan Peters}, editor = {Geoffrey J. Gordon and David B. Dunson and Miroslav Dud{\'{\i}}k}, title = {Relative Entropy Inverse Reinforcement Learning}, booktitle = {Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2011, Fort Lauderdale, USA, April 11-13, 2011}, series = {{JMLR} Proceedings}, volume = {15}, pages = {182--189}, publisher = {JMLR.org}, year = {2011}, url = {http://proceedings.mlr.press/v15/boularias11a/boularias11a.pdf}, timestamp = {Wed, 29 May 2019 08:41:44 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/BoulariasKP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1105-2416, author = {Yevgeny Seldin and Fran{\c{c}}ois Laviolette and John Shawe{-}Taylor and Jan Peters and Peter Auer}, title = {PAC-Bayesian Analysis of Martingales and Multiarmed Bandits}, journal = {CoRR}, volume = {abs/1105.2416}, year = {2011}, url = {http://arxiv.org/abs/1105.2416}, eprinttype = {arXiv}, eprint = {1105.2416}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1105-2416.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/corr/abs-1105-4585, author = {Yevgeny Seldin and Nicol{\`{o}} Cesa{-}Bianchi and Fran{\c{c}}ois Laviolette and Peter Auer and John Shawe{-}Taylor and Jan Peters}, title = {PAC-Bayesian Analysis of the Exploration-Exploitation Trade-off}, journal = {CoRR}, volume = {abs/1105.4585}, year = {2011}, url = {http://arxiv.org/abs/1105.4585}, eprinttype = {arXiv}, eprint = {1105.4585}, timestamp = {Mon, 13 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/corr/abs-1105-4585.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/dagstuhl-reports/WyattDLP11, author = {Jeremy L. Wyatt and Peter Dayan and Ales Leonardis and Jan Peters}, title = {Exploration and Curiosity in Robot Learning and Inference (Dagstuhl Seminar 11131)}, journal = {Dagstuhl Reports}, volume = {1}, number = {3}, pages = {67--95}, year = {2011}, url = {https://doi.org/10.4230/DagRep.1.3.67}, doi = {10.4230/DAGREP.1.3.67}, timestamp = {Wed, 07 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/dagstuhl-reports/WyattDLP11.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/at/PetersKS10, author = {Jan Peters and Jens Kober and Stefan Schaal}, title = {Algorithmen zum Automatischen Erlernen von Motorf{\"{a}}higkeiten (Policy Learning Algorithms for Motor Skills)}, journal = {Autom.}, volume = {58}, number = {12}, pages = {688--694}, year = {2010}, url = {https://doi.org/10.1524/auto.2010.0880}, doi = {10.1524/AUTO.2010.0880}, timestamp = {Wed, 22 Jul 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/at/PetersKS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/igpl/WierstraFPS10, author = {Daan Wierstra and Alexander F{\"{o}}rster and Jan Peters and J{\"{u}}rgen Schmidhuber}, title = {Recurrent policy gradients}, journal = {Log. J. {IGPL}}, volume = {18}, number = {5}, pages = {620--634}, year = {2010}, url = {https://doi.org/10.1093/jigpal/jzp049}, doi = {10.1093/JIGPAL/JZP049}, timestamp = {Fri, 06 Mar 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/igpl/WierstraFPS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/neco/MorimuraUYPD10, author = {Tetsuro Morimura and Eiji Uchibe and Junichiro Yoshimoto and Jan Peters and Kenji Doya}, title = {Derivatives of Logarithmic Stationary Distributions for Policy Gradient Reinforcement Learning}, journal = {Neural Comput.}, volume = {22}, number = {2}, pages = {342--376}, year = {2010}, url = {https://doi.org/10.1162/neco.2009.12-08-922}, doi = {10.1162/NECO.2009.12-08-922}, timestamp = {Tue, 01 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/neco/MorimuraUYPD10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/SehnkeORGPS10, author = {Frank Sehnke and Christian Osendorfer and Thomas R{\"{u}}ckstie{\ss} and Alex Graves and Jan Peters and J{\"{u}}rgen Schmidhuber}, title = {Parameter-exploring policy gradients}, journal = {Neural Networks}, volume = {23}, number = {4}, pages = {551--559}, year = {2010}, url = {https://doi.org/10.1016/j.neunet.2009.12.004}, doi = {10.1016/J.NEUNET.2009.12.004}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/SehnkeORGPS10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ram/KoberP10, author = {Jens Kober and Jan Peters}, title = {Imitation and Reinforcement Learning}, journal = {{IEEE} Robotics Autom. Mag.}, volume = {17}, number = {2}, pages = {55--62}, year = {2010}, url = {https://doi.org/10.1109/MRA.2010.936952}, doi = {10.1109/MRA.2010.936952}, timestamp = {Mon, 18 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ram/KoberP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ras/KromerDPP10, author = {Oliver Kroemer and Renaud Detry and Justus H. Piater and Jan Peters}, title = {Combining active learning and reactive control for robot grasping}, journal = {Robotics Auton. Syst.}, volume = {58}, number = {9}, pages = {1105--1116}, year = {2010}, url = {https://doi.org/10.1016/j.robot.2010.06.001}, doi = {10.1016/J.ROBOT.2010.06.001}, timestamp = {Mon, 24 Feb 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ras/KromerDPP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/scholarpedia/Peters10, author = {Jan Peters}, title = {Policy gradient methods}, journal = {Scholarpedia}, volume = {5}, number = {11}, pages = {3698}, year = {2010}, url = {https://doi.org/10.4249/scholarpedia.3698}, doi = {10.4249/SCHOLARPEDIA.3698}, timestamp = {Thu, 23 May 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/scholarpedia/Peters10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/PetersMA10, author = {Jan Peters and Katharina M{\"{u}}lling and Yasemin Altun}, editor = {Maria Fox and David Poole}, title = {Relative Entropy Policy Search}, booktitle = {Proceedings of the Twenty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI} 2010, Atlanta, Georgia, USA, July 11-15, 2010}, pages = {1607--1612}, publisher = {{AAAI} Press}, year = {2010}, url = {https://doi.org/10.1609/aaai.v24i1.7727}, doi = {10.1609/AAAI.V24I1.7727}, timestamp = {Mon, 04 Sep 2023 16:23:45 +0200}, biburl = {https://dblp.org/rec/conf/aaai/PetersMA10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/humanoids/MullingKP10, author = {Katharina M{\"{u}}lling and Jens Kober and Jan Peters}, title = {Learning table tennis with a Mixture of Motor Primitives}, booktitle = {10th {IEEE-RAS} International Conference on Humanoid Robots, Humanoids 2010, Nashville, TN, USA, December 6-8, 2010}, pages = {411--416}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ICHR.2010.5686298}, doi = {10.1109/ICHR.2010.5686298}, timestamp = {Wed, 16 Oct 2019 14:14:50 +0200}, biburl = {https://dblp.org/rec/conf/humanoids/MullingKP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icinco/KroemerDPP10, author = {Oliver Kroemer and Renaud Detry and Justus H. Piater and Jan Peters}, editor = {Joaquim Filipe and Juan Andrade{-}Cetto and Jean{-}Louis Ferrier}, title = {Grasping with Vision Descriptors and Motor Primitives}, booktitle = {{ICINCO} 2010, Proceedings of the 7th International Conference on Informatics in Control, Automation and Robotics, Volume 2, Funchal, Madeira, Portugal, June 15-18, 2010}, pages = {47--54}, publisher = {{INSTICC} Press}, year = {2010}, timestamp = {Tue, 16 Dec 2014 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icinco/KroemerDPP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icinco/KroemerDP010, author = {Oliver Kroemer and Renaud Detry and Justus H. Piater and Jan Peters}, editor = {Juan Andrade{-}Cetto and Jean{-}Louis Ferrier and Joaquim Filipe}, title = {Grasping with Vision Descriptors and Motor Primitives}, booktitle = {Informatics in Control, Automation and Robotics - Revised and Selected Papers from the International Conference on Informatics in Control, Automation and Robotics 2010, {ICINCO} 2010, Funchal, Madeira, Portugal, June 15-18, 2010}, series = {Lecture Notes in Electrical Engineering}, volume = {89}, pages = {211--223}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-19539-6\_14}, doi = {10.1007/978-3-642-19539-6\_14}, timestamp = {Sat, 19 Oct 2019 20:36:43 +0200}, biburl = {https://dblp.org/rec/conf/icinco/KroemerDP010.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KoberMKLSP10, author = {Jens Kober and Katharina M{\"{u}}lling and Oliver Kroemer and Christoph H. Lampert and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Movement templates for learning of hitting and batting}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2010, Anchorage, Alaska, USA, 3-7 May 2010}, pages = {853--858}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ROBOT.2010.5509672}, doi = {10.1109/ROBOT.2010.5509672}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icra/KoberMKLSP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/Nguyen-TuongP10, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Using model knowledge for learning inverse dynamics}, booktitle = {{IEEE} International Conference on Robotics and Automation, {ICRA} 2010, Anchorage, Alaska, USA, 3-7 May 2010}, pages = {2677--2682}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ROBOT.2010.5509858}, doi = {10.1109/ROBOT.2010.5509858}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/Nguyen-TuongP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/ErkanKDAPP10, author = {Ayse Erkan and Oliver Kroemer and Renaud Detry and Yasemin Altun and Justus H. Piater and Jan Peters}, title = {Learning probabilistic discriminative models of grasp affordances under limited supervision}, booktitle = {2010 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 18-22, 2010, Taipei, Taiwan}, pages = {1586--1591}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/IROS.2010.5650088}, doi = {10.1109/IROS.2010.5650088}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/ErkanKDAPP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/MullingKP10, author = {Katharina M{\"{u}}lling and Jens Kober and Jan Peters}, title = {A biomimetic approach to robot table tennis}, booktitle = {2010 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 18-22, 2010, Taipei, Taiwan}, pages = {1921--1926}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/IROS.2010.5650305}, doi = {10.1109/IROS.2010.5650305}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/MullingKP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iser/PetersMK10, author = {Jan Peters and Katharina M{\"{u}}lling and Jens Kober}, editor = {Oussama Khatib and Vijay Kumar and Gaurav S. Sukhatme}, title = {Experiments with Motor Primitives in Table Tennis}, booktitle = {Experimental Robotics - The 12th International Symposium on Experimental Robotics, {ISER} 2010, December 18-21, 2010, New Delhi and Agra, India}, series = {Springer Tracts in Advanced Robotics}, volume = {79}, pages = {347--359}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-28572-1\_24}, doi = {10.1007/978-3-642-28572-1\_24}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iser/PetersMK10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/AlvarezPSL10, author = {Mauricio A. {\'{A}}lvarez and Jan Peters and Bernhard Sch{\"{o}}lkopf and Neil D. Lawrence}, editor = {John D. Lafferty and Christopher K. I. Williams and John Shawe{-}Taylor and Richard S. Zemel and Aron Culotta}, title = {Switched Latent Force Models for Movement Segmentation}, booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada}, pages = {55--63}, publisher = {Curran Associates, Inc.}, year = {2010}, url = {https://proceedings.neurips.cc/paper/2010/hash/3a029f04d76d32e79367c4b3255dda4d-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/AlvarezPSL10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/ChiappaP10, author = {Silvia Chiappa and Jan Peters}, editor = {John D. Lafferty and Christopher K. I. Williams and John Shawe{-}Taylor and Richard S. Zemel and Aron Culotta}, title = {Movement extraction by detecting dynamics switches and repetitions}, booktitle = {Advances in Neural Information Processing Systems 23: 24th Annual Conference on Neural Information Processing Systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada}, pages = {388--396}, publisher = {Curran Associates, Inc.}, year = {2010}, url = {https://proceedings.neurips.cc/paper/2010/hash/704afe073992cbe4813cae2f7715336f-Abstract.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/ChiappaP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/KoberOP10, author = {Jens Kober and Erhan {\"{O}}ztop and Jan Peters}, editor = {Yoky Matsuoka and Hugh F. Durrant{-}Whyte and Jos{\'{e}} Neira}, title = {Reinforcement Learning to adjust Robot Movements to New Situations}, booktitle = {Robotics: Science and Systems VI, Universidad de Zaragoza, Zaragoza, Spain, June 27-30, 2010}, publisher = {The {MIT} Press}, year = {2010}, url = {http://www.roboticsproceedings.org/rss06/p05.html}, doi = {10.15607/RSS.2010.VI.005}, timestamp = {Thu, 23 Jun 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/rss/KoberOP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sab/KromerDPP10, author = {Oliver Kr{\"{o}}mer and Renaud Detry and Justus H. Piater and Jan Peters}, editor = {St{\'{e}}phane Doncieux and Beno{\^{\i}}t Girard and Agn{\`{e}}s Guillot and John Hallam and Jean{-}Arcady Meyer and Jean{-}Baptiste Mouret}, title = {Adapting Preshaped Grasping Movements Using Vision Descriptors}, booktitle = {From Animals to Animats 11, 11th International Conference on Simulation of Adaptive Behavior, {SAB} 2010, Paris - Clos Luc{\'{e}}, France, August 25-28, 2010. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {6226}, pages = {156--166}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-15193-4\_15}, doi = {10.1007/978-3-642-15193-4\_15}, timestamp = {Sat, 30 Sep 2023 09:55:34 +0200}, biburl = {https://dblp.org/rec/conf/sab/KromerDPP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/sab/MullingKP10, author = {Katharina M{\"{u}}lling and Jens Kober and Jan Peters}, editor = {St{\'{e}}phane Doncieux and Beno{\^{\i}}t Girard and Agn{\`{e}}s Guillot and John Hallam and Jean{-}Arcady Meyer and Jean{-}Baptiste Mouret}, title = {Simulating Human Table Tennis with a Biomimetic Robot Setup}, booktitle = {From Animals to Animats 11, 11th International Conference on Simulation of Adaptive Behavior, {SAB} 2010, Paris - Clos Luc{\'{e}}, France, August 25-28, 2010. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {6226}, pages = {273--282}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-15193-4\_26}, doi = {10.1007/978-3-642-15193-4\_26}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/sab/MullingKP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/smc/Gomez-RodriguezPHSGG10, author = {Manuel Gomez{-}Rodriguez and Jan Peters and N. Jeremy Hill and Bernhard Sch{\"{o}}lkopf and Alireza Gharabaghi and Moritz Grosse{-}Wentrup}, title = {Closing the sensorimotor loop: Haptic feedback facilitates decoding of arm movement imagery}, booktitle = {Proceedings of the {IEEE} International Conference on Systems, Man and Cybernetics, Istanbul, Turkey, 10-13 October 2010}, pages = {121--126}, publisher = {{IEEE}}, year = {2010}, url = {https://doi.org/10.1109/ICSMC.2010.5642217}, doi = {10.1109/ICSMC.2010.5642217}, timestamp = {Tue, 21 Mar 2023 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/smc/Gomez-RodriguezPHSGG10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:journals/jmlr/Nguyen-TuongP10, author = {Duy Nguyen{-}Tuong and Jan Peters}, editor = {Yee Whye Teh and D. Mike Titterington}, title = {Incremental Sparsification for Real-time Online Model Learning}, booktitle = {Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2010, Chia Laguna Resort, Sardinia, Italy, May 13-15, 2010}, series = {{JMLR} Proceedings}, volume = {9}, pages = {557--564}, publisher = {JMLR.org}, year = {2010}, url = {http://proceedings.mlr.press/v9/nguyen\_tuong10a.html}, timestamp = {Wed, 29 May 2019 08:41:44 +0200}, biburl = {https://dblp.org/rec/journals/jmlr/Nguyen-TuongP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/sci/SigaudP10, author = {Olivier Sigaud and Jan Peters}, editor = {Olivier Sigaud and Jan Peters}, title = {From Motor Learning to Interaction Learning in Robots}, booktitle = {From Motor Learning to Interaction Learning in Robots}, series = {Studies in Computational Intelligence}, volume = {264}, pages = {1--12}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-05181-4\_1}, doi = {10.1007/978-3-642-05181-4\_1}, timestamp = {Fri, 09 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/series/sci/SigaudP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/sci/Nguyen-TuongSP10, author = {Duy Nguyen{-}Tuong and Matthias W. Seeger and Jan Peters}, editor = {Olivier Sigaud and Jan Peters}, title = {Real-Time Local {GP} Model Learning}, booktitle = {From Motor Learning to Interaction Learning in Robots}, series = {Studies in Computational Intelligence}, volume = {264}, pages = {193--207}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-05181-4\_9}, doi = {10.1007/978-3-642-05181-4\_9}, timestamp = {Fri, 09 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/series/sci/Nguyen-TuongSP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/sci/KoberMP10, author = {Jens Kober and Betty J. Mohler and Jan Peters}, editor = {Olivier Sigaud and Jan Peters}, title = {Imitation and Reinforcement Learning for Motor Primitives with Perceptual Coupling}, booktitle = {From Motor Learning to Interaction Learning in Robots}, series = {Studies in Computational Intelligence}, volume = {264}, pages = {209--225}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-05181-4\_10}, doi = {10.1007/978-3-642-05181-4\_10}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/series/sci/KoberMP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:series/sci/DetryBPTKKPP10, author = {Renaud Detry and Emre Baseski and Mila Popovic and Younes Touati and Norbert Kr{\"{u}}ger and Oliver Kroemer and Jan Peters and Justus H. Piater}, editor = {Olivier Sigaud and Jan Peters}, title = {Learning Continuous Grasp Affordances by Sensorimotor Exploration}, booktitle = {From Motor Learning to Interaction Learning in Robots}, series = {Studies in Computational Intelligence}, volume = {264}, pages = {451--465}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-05181-4\_19}, doi = {10.1007/978-3-642-05181-4\_19}, timestamp = {Tue, 27 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/series/sci/DetryBPTKKPP10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@book{DBLP:series/sci/2010-264, editor = {Olivier Sigaud and Jan Peters}, title = {From Motor Learning to Interaction Learning in Robots}, series = {Studies in Computational Intelligence}, volume = {264}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-3-642-05181-4}, doi = {10.1007/978-3-642-05181-4}, isbn = {978-3-642-05180-7}, timestamp = {Tue, 16 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/series/sci/2010-264.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:reference/ml/PetersB10, author = {Jan Peters and J. Andrew Bagnell}, editor = {Claude Sammut and Geoffrey I. Webb}, title = {Policy Gradient Methods}, booktitle = {Encyclopedia of Machine Learning}, pages = {774--776}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-0-387-30164-8\_640}, doi = {10.1007/978-0-387-30164-8\_640}, timestamp = {Wed, 14 Nov 2018 10:51:34 +0100}, biburl = {https://dblp.org/rec/reference/ml/PetersB10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@incollection{DBLP:reference/ml/PetersTRM10, author = {Jan Peters and Russ Tedrake and Nicholas Roy and Jun Morimoto}, editor = {Claude Sammut and Geoffrey I. Webb}, title = {Robot Learning}, booktitle = {Encyclopedia of Machine Learning}, pages = {865--869}, publisher = {Springer}, year = {2010}, url = {https://doi.org/10.1007/978-0-387-30164-8\_732}, doi = {10.1007/978-0-387-30164-8\_732}, timestamp = {Wed, 12 Jul 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/reference/ml/PetersTRM10.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ar/Nguyen-TuongSP09, author = {Duy Nguyen{-}Tuong and Matthias W. Seeger and Jan Peters}, title = {Model Learning with Local Gaussian Process Regression}, journal = {Adv. Robotics}, volume = {23}, number = {15}, pages = {2015--2034}, year = {2009}, url = {https://doi.org/10.1163/016918609X12529286896877}, doi = {10.1163/016918609X12529286896877}, timestamp = {Sat, 25 Apr 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ar/Nguyen-TuongSP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/PetersN09, author = {Jan Peters and Andrew Y. Ng}, title = {Guest editorial: Special issue on robot learning, Part {A}}, journal = {Auton. Robots}, volume = {27}, number = {1}, pages = {1--2}, year = {2009}, url = {https://doi.org/10.1007/s10514-009-9122-2}, doi = {10.1007/S10514-009-9122-2}, timestamp = {Mon, 05 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/PetersN09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/PetersN09a, author = {Jan Peters and Andrew Y. Ng}, title = {Guest editorial: Special issue on robot learning, Part {B}}, journal = {Auton. Robots}, volume = {27}, number = {2}, pages = {91--92}, year = {2009}, url = {https://doi.org/10.1007/s10514-009-9131-1}, doi = {10.1007/S10514-009-9131-1}, timestamp = {Mon, 05 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/arobots/PetersN09a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijon/DeisenrothRP09, author = {Marc Peter Deisenroth and Carl Edward Rasmussen and Jan Peters}, title = {Gaussian process dynamic programming}, journal = {Neurocomputing}, volume = {72}, number = {7-9}, pages = {1508--1524}, year = {2009}, url = {https://doi.org/10.1016/j.neucom.2008.12.019}, doi = {10.1016/J.NEUCOM.2008.12.019}, timestamp = {Sun, 02 Jun 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijon/DeisenrothRP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ki/Kober009, author = {Jens Kober and Jan Peters}, title = {Policy Search for Motor Primitives}, journal = {K{\"{u}}nstliche Intell.}, volume = {23}, number = {3}, pages = {38--40}, year = {2009}, url = {http://www.kuenstliche-intelligenz.de/fileadmin/template/main/archiv/pdf/ki2009-03\_page38-40\_web\_full.pdf}, timestamp = {Fri, 27 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ki/Kober009.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/HachiyaASP09, author = {Hirotaka Hachiya and Takayuki Akiyama and Masashi Sugiyama and Jan Peters}, title = {Adaptive importance sampling for value function approximation in off-policy reinforcement learning}, journal = {Neural Networks}, volume = {22}, number = {10}, pages = {1399--1410}, year = {2009}, url = {https://doi.org/10.1016/j.neunet.2009.01.002}, doi = {10.1016/J.NEUNET.2009.01.002}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/HachiyaASP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ram/PetersMTR09, author = {Jan Peters and Jun Morimoto and Russ Tedrake and Nicholas Roy}, title = {Robot learning {[TC} Spotlight]}, journal = {{IEEE} Robotics Autom. Mag.}, volume = {16}, number = {3}, pages = {19--20}, year = {2009}, url = {https://doi.org/10.1109/MRA.2009.933618}, doi = {10.1109/MRA.2009.933618}, timestamp = {Mon, 18 May 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ram/PetersMTR09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/adprl/HachiyaASP09, author = {Hirotaka Hachiya and Takayuki Akiyama and Masashi Sugiyama and Jan Peters}, title = {Efficient data reuse in value function approximation}, booktitle = {{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement Learning, {ADPRL} 2009, Nashville, TN, USA, March 31 - April 1, 2009}, pages = {8--15}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ADPRL.2009.4927519}, doi = {10.1109/ADPRL.2009.4927519}, timestamp = {Wed, 16 Oct 2019 14:14:48 +0200}, biburl = {https://dblp.org/rec/conf/adprl/HachiyaASP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/adprl/PetersK09, author = {Jan Peters and Jens Kober}, title = {Using reward-weighted imitation for robot Reinforcement Learning}, booktitle = {{IEEE} Symposium on Adaptive Dynamic Programming and Reinforcement Learning, {ADPRL} 2009, Nashville, TN, USA, March 31 - April 1, 2009}, pages = {226--232}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ADPRL.2009.4927549}, doi = {10.1109/ADPRL.2009.4927549}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/adprl/PetersK09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ams/MullingP09, author = {Katharina M{\"{u}}lling and Jan Peters}, editor = {R{\"{u}}diger Dillmann and J{\"{u}}rgen Beyerer and Christoph Stiller and Johann Marius Z{\"{o}}llner and Tobias Gindele}, title = {A Computational Model of Human Table Tennis for Robot Application}, booktitle = {Autonome Mobile Systeme 2009 - 21. Fachgespr{\"{a}}ch, Karlsruhe, 3./4. Dezember 2009}, series = {Informatik Aktuell}, pages = {57--64}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-10284-4\_8}, doi = {10.1007/978-3-642-10284-4\_8}, timestamp = {Tue, 23 May 2017 01:06:08 +0200}, biburl = {https://dblp.org/rec/conf/ams/MullingP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ams/KoberP09, author = {Jens Kober and Jan Peters}, editor = {R{\"{u}}diger Dillmann and J{\"{u}}rgen Beyerer and Christoph Stiller and Johann Marius Z{\"{o}}llner and Tobias Gindele}, title = {Learning New Basic Movements for Robotics}, booktitle = {Autonome Mobile Systeme 2009 - 21. Fachgespr{\"{a}}ch, Karlsruhe, 3./4. Dezember 2009}, series = {Informatik Aktuell}, pages = {105--112}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-10284-4\_14}, doi = {10.1007/978-3-642-10284-4\_14}, timestamp = {Mon, 16 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/ams/KoberP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dagm/LampertP09, author = {Christoph H. Lampert and Jan Peters}, editor = {Joachim Denzler and Gunther Notni and Herbert S{\"{u}}{\ss}e}, title = {Active Structured Learning for High-Speed Object Detection}, booktitle = {Pattern Recognition, 31st {DAGM} Symposium, Jena, Germany, September 9-11, 2009. Proceedings}, series = {Lecture Notes in Computer Science}, volume = {5748}, pages = {221--231}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-03798-6\_23}, doi = {10.1007/978-3-642-03798-6\_23}, timestamp = {Tue, 14 May 2019 10:00:52 +0200}, biburl = {https://dblp.org/rec/conf/dagm/LampertP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/NeumannMP09, author = {Gerhard Neumann and Wolfgang Maass and Jan Peters}, editor = {Andrea Pohoreckyj Danyluk and L{\'{e}}on Bottou and Michael L. Littman}, title = {Learning complex motions by sequencing simpler motion templates}, booktitle = {Proceedings of the 26th Annual International Conference on Machine Learning, {ICML} 2009, Montreal, Quebec, Canada, June 14-18, 2009}, series = {{ACM} International Conference Proceeding Series}, volume = {382}, pages = {753--760}, publisher = {{ACM}}, year = {2009}, url = {https://doi.org/10.1145/1553374.1553471}, doi = {10.1145/1553374.1553471}, timestamp = {Tue, 06 Nov 2018 16:58:29 +0100}, biburl = {https://dblp.org/rec/conf/icml/NeumannMP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/KoberP09, author = {Jens Kober and Jan Peters}, title = {Learning motor primitives for robotics}, booktitle = {2009 {IEEE} International Conference on Robotics and Automation, {ICRA} 2009, Kobe, Japan, May 12-17, 2009}, pages = {2112--2118}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/ROBOT.2009.5152577}, doi = {10.1109/ROBOT.2009.5152577}, timestamp = {Mon, 16 Sep 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/KoberP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KroemerDPP09, author = {Oliver Kroemer and Renaud Detry and Justus H. Piater and Jan Peters}, title = {Active learning using mean shift optimization for robot grasping}, booktitle = {2009 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 11-15, 2009, St. Louis, MO, {USA}}, pages = {2610--2615}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/IROS.2009.5354345}, doi = {10.1109/IROS.2009.5354345}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/KroemerDPP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Nguyen-TuongSP09, author = {Duy Nguyen{-}Tuong and Bernhard Sch{\"{o}}lkopf and Jan Peters}, title = {Sparse online model learning for robot control with support vector regression}, booktitle = {2009 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 11-15, 2009, St. Louis, MO, {USA}}, pages = {3121--3126}, publisher = {{IEEE}}, year = {2009}, url = {https://doi.org/10.1109/IROS.2009.5354609}, doi = {10.1109/IROS.2009.5354609}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/Nguyen-TuongSP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isrr/PiaterJDKKKP09, author = {Justus H. Piater and S{\'{e}}bastien Jodogne and Renaud Detry and Dirk Kraft and Norbert Kr{\"{u}}ger and Oliver Kr{\"{o}}mer and Jan Peters}, editor = {C{\'{e}}dric Pradalier and Roland Siegwart and Gerhard Hirzinger}, title = {Learning Visual Representations for Interactive Systems}, booktitle = {Robotics Research - The 14th International Symposium, {ISRR} 2009, August 31 - September 3, 2009, Lucerne, Switzerland}, series = {Springer Tracts in Advanced Robotics}, volume = {70}, pages = {399--416}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-19457-3\_24}, doi = {10.1007/978-3-642-19457-3\_24}, timestamp = {Sun, 06 Aug 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/isrr/PiaterJDKKKP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isrr/PetersMKNK09, author = {Jan Peters and Katharina M{\"{u}}lling and Jens Kober and Duy Nguyen{-}Tuong and Oliver Kr{\"{o}}mer}, editor = {C{\'{e}}dric Pradalier and Roland Siegwart and Gerhard Hirzinger}, title = {Towards Motor Skill Learning for Robotics}, booktitle = {Robotics Research - The 14th International Symposium, {ISRR} 2009, August 31 - September 3, 2009, Lucerne, Switzerland}, series = {Springer Tracts in Advanced Robotics}, volume = {70}, pages = {469--482}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-19457-3\_28}, doi = {10.1007/978-3-642-19457-3\_28}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/isrr/PetersMKNK09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/pkdd/HachiyaPS09, author = {Hirotaka Hachiya and Jan Peters and Masashi Sugiyama}, editor = {Wray L. Buntine and Marko Grobelnik and Dunja Mladenic and John Shawe{-}Taylor}, title = {Efficient Sample Reuse in EM-Based Policy Search}, booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference, {ECML} {PKDD} 2009, Bled, Slovenia, September 7-11, 2009, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {5781}, pages = {469--484}, publisher = {Springer}, year = {2009}, url = {https://doi.org/10.1007/978-3-642-04180-8\_48}, doi = {10.1007/978-3-642-04180-8\_48}, timestamp = {Tue, 14 May 2019 10:00:47 +0200}, biburl = {https://dblp.org/rec/conf/pkdd/HachiyaPS09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:journals/jmlr/HoffmanFDP09, author = {Matthew Hoffman and Nando de Freitas and Arnaud Doucet and Jan Peters}, editor = {David A. Van Dyk and Max Welling}, title = {An Expectation Maximization Algorithm for Continuous Markov Decision Processes with Arbitrary Reward}, booktitle = {Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics, {AISTATS} 2009, Clearwater Beach, Florida, USA, April 16-18, 2009}, series = {{JMLR} Proceedings}, volume = {5}, pages = {232--239}, publisher = {JMLR.org}, year = {2009}, url = {http://proceedings.mlr.press/v5/hoffman09a.html}, timestamp = {Thu, 03 Dec 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/jmlr/HoffmanFDP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@proceedings{DBLP:conf/dagstuhl/2009P9341, editor = {Michael Beetz and Oliver Brock and Gordon Cheng and Jan Peters}, title = {Cognition, Control and Learning for Robot Manipulation in Human Environments, 16.08. - 21.08.2009}, series = {Dagstuhl Seminar Proceedings}, volume = {09341}, publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik, Germany}, year = {2009}, url = {http://drops.dagstuhl.de/portals/09341/}, timestamp = {Thu, 10 Jun 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/dagstuhl/2009P9341.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dagstuhl/BeetzBCP09, author = {Michael Beetz and Oliver Brock and Gordon Cheng and Jan Peters}, editor = {Michael Beetz and Oliver Brock and Gordon Cheng and Jan Peters}, title = {09341 Abstracts Collection - Cognition, Control and Learning for Robot Manipulation in Human Environments}, booktitle = {Cognition, Control and Learning for Robot Manipulation in Human Environments, 16.08. - 21.08.2009}, series = {Dagstuhl Seminar Proceedings}, volume = {09341}, publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik, Germany}, year = {2009}, url = {http://drops.dagstuhl.de/opus/volltexte/2010/2366/}, timestamp = {Thu, 10 Jun 2021 13:02:10 +0200}, biburl = {https://dblp.org/rec/conf/dagstuhl/BeetzBCP09.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/dagstuhl/BeetzBCP09a, author = {Michael Beetz and Oliver Brock and Gordon Cheng and Jan Peters}, editor = {Michael Beetz and Oliver Brock and Gordon Cheng and Jan Peters}, title = {09341 Summary - Cognition, Control and Learning for Robot Manipulation in Human Environments}, booktitle = {Cognition, Control and Learning for Robot Manipulation in Human Environments, 16.08. - 21.08.2009}, series = {Dagstuhl Seminar Proceedings}, volume = {09341}, publisher = {Schloss Dagstuhl - Leibniz-Zentrum f{\"{u}}r Informatik, Germany}, year = {2009}, url = {http://drops.dagstuhl.de/opus/volltexte/2010/2364/}, timestamp = {Thu, 23 Aug 2018 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/dagstuhl/BeetzBCP09a.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/arobots/PetersMUNS08, author = {Jan Peters and Michael N. Mistry and Firdaus E. Udwadia and Jun Nakanishi and Stefan Schaal}, title = {A unifying framework for robot control with redundant DOFs}, journal = {Auton. Robots}, volume = {24}, number = {1}, pages = {1--12}, year = {2008}, url = {https://doi.org/10.1007/s10514-007-9051-x}, doi = {10.1007/S10514-007-9051-X}, timestamp = {Fri, 08 Mar 2024 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/arobots/PetersMUNS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cgf/SteinkeHPS08, author = {Florian Steinke and Matthias Hein and Jan Peters and Bernhard Sch{\"{o}}lkopf}, title = {Manifold-valued Thin-Plate Splines with Applications in Computer Graphics}, journal = {Comput. Graph. Forum}, volume = {27}, number = {2}, pages = {437--448}, year = {2008}, url = {https://doi.org/10.1111/j.1467-8659.2008.01141.x}, doi = {10.1111/J.1467-8659.2008.01141.X}, timestamp = {Mon, 26 Oct 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/cgf/SteinkeHPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijon/PetersS08, author = {Jan Peters and Stefan Schaal}, title = {Natural Actor-Critic}, journal = {Neurocomputing}, volume = {71}, number = {7-9}, pages = {1180--1190}, year = {2008}, url = {https://doi.org/10.1016/j.neucom.2007.11.026}, doi = {10.1016/J.NEUCOM.2007.11.026}, timestamp = {Tue, 06 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijon/PetersS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/PetersS08, author = {Jan Peters and Stefan Schaal}, title = {Learning to Control in Operational Space}, journal = {Int. J. Robotics Res.}, volume = {27}, number = {2}, pages = {197--212}, year = {2008}, url = {https://doi.org/10.1177/0278364907087548}, doi = {10.1177/0278364907087548}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/PetersS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ijrr/NakanishiCMPS08, author = {Jun Nakanishi and Rick Cory and Michael N. Mistry and Jan Peters and Stefan Schaal}, title = {Operational Space Control: {A} Theoretical and Empirical Comparison}, journal = {Int. J. Robotics Res.}, volume = {27}, number = {6}, pages = {737--757}, year = {2008}, url = {https://doi.org/10.1177/0278364908091463}, doi = {10.1177/0278364908091463}, timestamp = {Thu, 17 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/ijrr/NakanishiCMPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/ki/Peters08, author = {Jan Peters}, title = {Machine Learning for motor skills in robotics}, journal = {K{\"{u}}nstliche Intell.}, volume = {22}, number = {4}, pages = {41--43}, year = {2008}, url = {http://www.kuenstliche-intelligenz.de/fileadmin/template/main/archiv/pdf/ki2008-04\_page41\_web\_teaser.pdf}, timestamp = {Fri, 27 Nov 2020 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/ki/Peters08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/nn/PetersS08, author = {Jan Peters and Stefan Schaal}, title = {Reinforcement learning of motor skills with policy gradients}, journal = {Neural Networks}, volume = {21}, number = {4}, pages = {682--697}, year = {2008}, url = {https://doi.org/10.1016/j.neunet.2008.02.003}, doi = {10.1016/J.NEUNET.2008.02.003}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/journals/nn/PetersS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/aaai/HachiyaASP08, author = {Hirotaka Hachiya and Takayuki Akiyama and Masashi Sugiyama and Jan Peters}, editor = {Dieter Fox and Carla P. Gomes}, title = {Adaptive Importance Sampling with Automatic Model Selection in Value Function Approximation}, booktitle = {Proceedings of the Twenty-Third {AAAI} Conference on Artificial Intelligence, {AAAI} 2008, Chicago, Illinois, USA, July 13-17, 2008}, pages = {1351--1356}, publisher = {{AAAI} Press}, year = {2008}, url = {http://www.aaai.org/Library/AAAI/2008/aaai08-214.php}, timestamp = {Tue, 05 Sep 2023 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/aaai/HachiyaASP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/Nguyen-TuongS008, author = {Duy Nguyen{-}Tuong and Matthias W. Seeger and Jan Peters}, title = {Computed torque control with nonparametric regression models}, booktitle = {American Control Conference, {ACC} 2008, Seattle, WA, USA, 11-13 June 2008}, pages = {212--217}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/ACC.2008.4586493}, doi = {10.1109/ACC.2008.4586493}, timestamp = {Fri, 03 Dec 2021 13:02:23 +0100}, biburl = {https://dblp.org/rec/conf/amcc/Nguyen-TuongS008.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/amcc/Deisenroth0R08, author = {Marc Peter Deisenroth and Jan Peters and Carl E. Rasmussen}, title = {Approximate dynamic programming with Gaussian processes}, booktitle = {American Control Conference, {ACC} 2008, Seattle, WA, USA, 11-13 June 2008}, pages = {4480--4485}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/ACC.2008.4587201}, doi = {10.1109/ACC.2008.4587201}, timestamp = {Sat, 05 Sep 2020 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/amcc/Deisenroth0R08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/cec/WierstraSPS08, author = {Daan Wierstra and Tom Schaul and Jan Peters and J{\"{u}}rgen Schmidhuber}, title = {Natural Evolution Strategies}, booktitle = {Proceedings of the {IEEE} Congress on Evolutionary Computation, {CEC} 2008, June 1-6, 2008, Hong Kong, China}, pages = {3381--3387}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/CEC.2008.4631255}, doi = {10.1109/CEC.2008.4631255}, timestamp = {Thu, 16 Dec 2021 14:01:33 +0100}, biburl = {https://dblp.org/rec/conf/cec/WierstraSPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/esann/Nguyen-TuongPSS08, author = {Duy Nguyen{-}Tuong and Jan Peters and Matthias W. Seeger and Bernhard Sch{\"{o}}lkopf}, title = {Learning Inverse Dynamics: a Comparison}, booktitle = {16th European Symposium on Artificial Neural Networks, {ESANN} 2008, Bruges, Belgium, April 23-25, 2008, Proceedings}, pages = {13--18}, year = {2008}, url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2008-46.pdf}, timestamp = {Tue, 02 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/esann/Nguyen-TuongPSS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/esann/DeisenrothRP08, author = {Marc Peter Deisenroth and Carl Edward Rasmussen and Jan Peters}, title = {Model-Based Reinforcement Learning with Continuous States and Actions}, booktitle = {16th European Symposium on Artificial Neural Networks, {ESANN} 2008, Bruges, Belgium, April 23-25, 2008, Proceedings}, pages = {19--24}, year = {2008}, url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2008-8.pdf}, timestamp = {Tue, 02 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/esann/DeisenrothRP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ewrl/PetersKN08, author = {Jan Peters and Jens Kober and Duy Nguyen{-}Tuong}, editor = {Sertan Girgin and Manuel Loth and R{\'{e}}mi Munos and Philippe Preux and Daniil Ryabko}, title = {Policy Learning - {A} Unified Perspective with Applications in Robotics}, booktitle = {Recent Advances in Reinforcement Learning, 8th European Workshop, {EWRL} 2008, Villeneuve d'Ascq, France, June 30 - July 3, 2008, Revised and Selected Papers}, series = {Lecture Notes in Computer Science}, volume = {5323}, pages = {220--228}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-89722-4\_17}, doi = {10.1007/978-3-540-89722-4\_17}, timestamp = {Tue, 14 May 2019 10:00:48 +0200}, biburl = {https://dblp.org/rec/conf/ewrl/PetersKN08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/SehnkeORGPS08, author = {Frank Sehnke and Christian Osendorfer and Thomas R{\"{u}}ckstie{\ss} and Alex Graves and Jan Peters and J{\"{u}}rgen Schmidhuber}, editor = {Vera Kurkov{\'{a}} and Roman Neruda and Jan Koutn{\'{\i}}k}, title = {Policy Gradients with Parameter-Based Exploration for Control}, booktitle = {Artificial Neural Networks - {ICANN} 2008 , 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {5163}, pages = {387--396}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-87536-9\_40}, doi = {10.1007/978-3-540-87536-9\_40}, timestamp = {Tue, 14 May 2019 10:00:49 +0200}, biburl = {https://dblp.org/rec/conf/icann/SehnkeORGPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/WierstraSPS08, author = {Daan Wierstra and Tom Schaul and Jan Peters and J{\"{u}}rgen Schmidhuber}, editor = {Vera Kurkov{\'{a}} and Roman Neruda and Jan Koutn{\'{\i}}k}, title = {Episodic Reinforcement Learning by Logistic Reward-Weighted Regression}, booktitle = {Artificial Neural Networks - {ICANN} 2008 , 18th International Conference, Prague, Czech Republic, September 3-6, 2008, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {5163}, pages = {407--416}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-87536-9\_42}, doi = {10.1007/978-3-540-87536-9\_42}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icann/WierstraSPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/PetersN08, author = {Jan Peters and Duy Nguyen{-}Tuong}, title = {Real-time learning of resolved velocity control on a Mitsubishi {PA-10}}, booktitle = {2008 {IEEE} International Conference on Robotics and Automation, {ICRA} 2008, May 19-23, 2008, Pasadena, California, {USA}}, pages = {2872--2877}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/ROBOT.2008.4543645}, doi = {10.1109/ROBOT.2008.4543645}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/PetersN08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/Nguyen-TuongP08, author = {Duy Nguyen{-}Tuong and Jan Peters}, title = {Local Gaussian process regression for real-time model-based robot control}, booktitle = {2008 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, September 22-26, 2008, Acropolis Convention Center, Nice, France}, pages = {380--385}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/IROS.2008.4650850}, doi = {10.1109/IROS.2008.4650850}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/Nguyen-TuongP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/KoberMP08, author = {Jens Kober and Betty J. Mohler and Jan Peters}, title = {Learning perceptual coupling for motor primitives}, booktitle = {2008 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, September 22-26, 2008, Acropolis Convention Center, Nice, France}, pages = {834--839}, publisher = {{IEEE}}, year = {2008}, url = {https://doi.org/10.1109/IROS.2008.4650953}, doi = {10.1109/IROS.2008.4650953}, timestamp = {Wed, 14 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/iros/KoberMP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/ChiappaKP08, author = {Silvia Chiappa and Jens Kober and Jan Peters}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and L{\'{e}}on Bottou}, title = {Using Bayesian Dynamical Systems for Motion Template Libraries}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, pages = {297--304}, publisher = {Curran Associates, Inc.}, year = {2008}, url = {https://proceedings.neurips.cc/paper/2008/hash/65658fde58ab3c2b6e5132a39fae7cb9-Abstract.html}, timestamp = {Mon, 16 May 2022 15:41:51 +0200}, biburl = {https://dblp.org/rec/conf/nips/ChiappaKP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/KoberP08, author = {Jens Kober and Jan Peters}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and L{\'{e}}on Bottou}, title = {Policy Search for Motor Primitives in Robotics}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, pages = {849--856}, publisher = {Curran Associates, Inc.}, year = {2008}, url = {https://proceedings.neurips.cc/paper/2008/hash/7647966b7343c29048673252e490f736-Abstract.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/KoberP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/NeumannP08, author = {Gerhard Neumann and Jan Peters}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and L{\'{e}}on Bottou}, title = {Fitted Q-iteration by Advantage Weighted Regression}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, pages = {1177--1184}, publisher = {Curran Associates, Inc.}, year = {2008}, url = {https://proceedings.neurips.cc/paper/2008/hash/f79921bbae40a577928b76d2fc3edc2a-Abstract.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/NeumannP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/nips/Nguyen-TuongSP08, author = {Duy Nguyen{-}Tuong and Matthias W. Seeger and Jan Peters}, editor = {Daphne Koller and Dale Schuurmans and Yoshua Bengio and L{\'{e}}on Bottou}, title = {Local Gaussian Process Regression for Real Time Online Model Learning}, booktitle = {Advances in Neural Information Processing Systems 21, Proceedings of the Twenty-Second Annual Conference on Neural Information Processing Systems, Vancouver, British Columbia, Canada, December 8-11, 2008}, pages = {1193--1200}, publisher = {Curran Associates, Inc.}, year = {2008}, url = {https://proceedings.neurips.cc/paper/2008/hash/01161aaa0b6d1345dd8fe4e481144d84-Abstract.html}, timestamp = {Thu, 21 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/nips/Nguyen-TuongSP08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ppsn/WierstraSPS08, author = {Daan Wierstra and Tom Schaul and Jan Peters and J{\"{u}}rgen Schmidhuber}, editor = {G{\"{u}}nter Rudolph and Thomas Jansen and Simon M. Lucas and Carlo Poloni and Nicola Beume}, title = {Fitness Expectation Maximization}, booktitle = {Parallel Problem Solving from Nature - {PPSN} X, 10th International Conference Dortmund, Germany, September 13-17, 2008, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {5199}, pages = {337--346}, publisher = {Springer}, year = {2008}, url = {https://doi.org/10.1007/978-3-540-87700-4\_34}, doi = {10.1007/978-3-540-87700-4\_34}, timestamp = {Tue, 14 May 2019 10:00:53 +0200}, biburl = {https://dblp.org/rec/conf/ppsn/WierstraSPS08.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/cj/Peters07, author = {Jan Peters}, title = {Computational Intelligence: Principles, Techniques and Applications}, journal = {Comput. J.}, volume = {50}, number = {6}, pages = {758}, year = {2007}, url = {https://doi.org/10.1093/comjnl/bxm073}, doi = {10.1093/COMJNL/BXM073}, timestamp = {Sat, 20 May 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/cj/Peters07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ams/PetersSS07, author = {Jan Peters and Stefan Schaal and Bernhard Sch{\"{o}}lkopf}, editor = {Karsten Berns and Tobias Luksch}, title = {Towards Machine Learning of Motor Skills}, booktitle = {Autonome Mobile Systeme 2007, 20. Fachgespr{\"{a}}ch, Kaiserslautern, 18./19. Oktober 2007}, series = {Informatik Aktuell}, pages = {138--144}, publisher = {Springer}, year = {2007}, url = {https://doi.org/10.1007/978-3-540-74764-2\_22}, doi = {10.1007/978-3-540-74764-2\_22}, timestamp = {Tue, 23 May 2017 01:06:08 +0200}, biburl = {https://dblp.org/rec/conf/ams/PetersSS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/esann/PetersS07, author = {Jan Peters and Stefan Schaal}, title = {Applying the Episodic Natural Actor-Critic Architecture to Motor Primitive Learning}, booktitle = {15th European Symposium on Artificial Neural Networks, {ESANN} 2007, Bruges, Belgium, April 25-27, 2007, Proceedings}, pages = {295--300}, year = {2007}, url = {https://www.esann.org/sites/default/files/proceedings/legacy/es2007-125.pdf}, timestamp = {Tue, 02 Aug 2022 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/esann/PetersS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icann/WierstraFPS07, author = {Daan Wierstra and Alexander F{\"{o}}rster and Jan Peters and J{\"{u}}rgen Schmidhuber}, editor = {Joaquim Marques de S{\'{a}} and Lu{\'{\i}}s A. Alexandre and Wlodzislaw Duch and Danilo P. Mandic}, title = {Solving Deep Memory POMDPs with Recurrent Policy Gradients}, booktitle = {Artificial Neural Networks - {ICANN} 2007, 17th International Conference, Porto, Portugal, September 9-13, 2007, Proceedings, Part {I}}, series = {Lecture Notes in Computer Science}, volume = {4668}, pages = {697--706}, publisher = {Springer}, year = {2007}, url = {https://doi.org/10.1007/978-3-540-74690-4\_71}, doi = {10.1007/978-3-540-74690-4\_71}, timestamp = {Tue, 14 May 2019 10:00:49 +0200}, biburl = {https://dblp.org/rec/conf/icann/WierstraFPS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icml/PetersS07, author = {Jan Peters and Stefan Schaal}, editor = {Zoubin Ghahramani}, title = {Reinforcement learning by reward-weighted regression for operational space control}, booktitle = {Machine Learning, Proceedings of the Twenty-Fourth International Conference {(ICML} 2007), Corvallis, Oregon, USA, June 20-24, 2007}, series = {{ACM} International Conference Proceeding Series}, volume = {227}, pages = {745--750}, publisher = {{ACM}}, year = {2007}, url = {https://doi.org/10.1145/1273496.1273590}, doi = {10.1145/1273496.1273590}, timestamp = {Tue, 06 Nov 2018 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/icml/PetersS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iconip/PetersS07, author = {Jan Peters and Stefan Schaal}, editor = {Masumi Ishikawa and Kenji Doya and Hiroyuki Miyamoto and Takeshi Yamakawa}, title = {Policy Learning for Motor Skills}, booktitle = {Neural Information Processing, 14th International Conference, {ICONIP} 2007, Kitakyushu, Japan, November 13-16, 2007, Revised Selected Papers, Part {II}}, series = {Lecture Notes in Computer Science}, volume = {4985}, pages = {233--242}, publisher = {Springer}, year = {2007}, url = {https://doi.org/10.1007/978-3-540-69162-4\_25}, doi = {10.1007/978-3-540-69162-4\_25}, timestamp = {Tue, 14 May 2019 10:00:42 +0200}, biburl = {https://dblp.org/rec/conf/iconip/PetersS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/icra/PetersS07, author = {Jan Peters and Stefan Schaal}, title = {Reinforcement Learning for Operational Space Control}, booktitle = {2007 {IEEE} International Conference on Robotics and Automation, {ICRA} 2007, 10-14 April 2007, Roma, Italy}, pages = {2111--2116}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/ROBOT.2007.363633}, doi = {10.1109/ROBOT.2007.363633}, timestamp = {Sun, 04 Jun 2017 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/icra/PetersS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/NakanishiMPS07, author = {Jun Nakanishi and Michael N. Mistry and Jan Peters and Stefan Schaal}, title = {Towards compliant humanoids-an experimental assessment of suitable task space position/orientation controllers}, booktitle = {2007 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, October 29 - November 2, 2007, Sheraton Hotel and Marina, San Diego, California, {USA}}, pages = {2520--2527}, publisher = {{IEEE}}, year = {2007}, url = {https://doi.org/10.1109/IROS.2007.4399562}, doi = {10.1109/IROS.2007.4399562}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/NakanishiMPS07.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ijcnn/PetersS06, author = {Jan Peters and Stefan Schaal}, title = {Reinforcement Learning for Parameterized Motor Primitives}, booktitle = {Proceedings of the International Joint Conference on Neural Networks, {IJCNN} 2006, part of the {IEEE} World Congress on Computational Intelligence, {WCCI} 2006, Vancouver, BC, Canada, 16-21 July 2006}, pages = {73--80}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/IJCNN.2006.246662}, doi = {10.1109/IJCNN.2006.246662}, timestamp = {Tue, 10 Aug 2021 14:29:47 +0200}, biburl = {https://dblp.org/rec/conf/ijcnn/PetersS06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/PetersS06, author = {Jan Peters and Stefan Schaal}, title = {Policy Gradient Methods for Robotics}, booktitle = {2006 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, {IROS} 2006, October 9-15, 2006, Beijing, China}, pages = {2219--2225}, publisher = {{IEEE}}, year = {2006}, url = {https://doi.org/10.1109/IROS.2006.282564}, doi = {10.1109/IROS.2006.282564}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/PetersS06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/PetersS06, author = {Jan Peters and Stefan Schaal}, editor = {Gaurav S. Sukhatme and Stefan Schaal and Wolfram Burgard and Dieter Fox}, title = {Learning Operational Space Control}, booktitle = {Robotics: Science and Systems II, August 16-19, 2006. University of Pennsylvania, Philadelphia, Pennsylvania, {USA}}, publisher = {The {MIT} Press}, year = {2006}, url = {http://www.roboticsproceedings.org/rss02/p33.html}, doi = {10.15607/RSS.2006.II.033}, timestamp = {Fri, 29 Jan 2021 22:08:23 +0100}, biburl = {https://dblp.org/rec/conf/rss/PetersS06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/rss/TingMPSN06, author = {Jo{-}Anne Ting and Michael N. Mistry and Jan Peters and Stefan Schaal and Jun Nakanishi}, editor = {Gaurav S. Sukhatme and Stefan Schaal and Wolfram Burgard and Dieter Fox}, title = {A Bayesian Approach to Nonlinear Parameter Identification for Rigid Body Dynamics}, booktitle = {Robotics: Science and Systems II, August 16-19, 2006. University of Pennsylvania, Philadelphia, Pennsylvania, {USA}}, publisher = {The {MIT} Press}, year = {2006}, url = {http://www.roboticsproceedings.org/rss02/p32.html}, doi = {10.15607/RSS.2006.II.032}, timestamp = {Fri, 29 Jan 2021 00:00:00 +0100}, biburl = {https://dblp.org/rec/conf/rss/TingMPSN06.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/ecml/PetersVS05, author = {Jan Peters and Sethu Vijayakumar and Stefan Schaal}, editor = {Jo{\~{a}}o Gama and Rui Camacho and Pavel Brazdil and Al{\'{\i}}pio Jorge and Lu{\'{\i}}s Torgo}, title = {Natural Actor-Critic}, booktitle = {Machine Learning: {ECML} 2005, 16th European Conference on Machine Learning, Porto, Portugal, October 3-7, 2005, Proceedings}, series = {Lecture Notes in Computer Science}, volume = {3720}, pages = {280--291}, publisher = {Springer}, year = {2005}, url = {https://doi.org/10.1007/11564096\_29}, doi = {10.1007/11564096\_29}, timestamp = {Wed, 24 Mar 2021 17:12:00 +0100}, biburl = {https://dblp.org/rec/conf/ecml/PetersVS05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/PetersMUCNS05, author = {Jan Peters and Michael N. Mistry and Firdaus E. Udwadia and Rick Cory and Jun Nakanishi and Stefan Schaal}, title = {A unifying methodology for the control of robotic systems}, booktitle = {2005 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, August 2-6, 2005}, pages = {1824--1831}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/IROS.2005.1545516}, doi = {10.1109/IROS.2005.1545516}, timestamp = {Wed, 16 Oct 2019 14:14:51 +0200}, biburl = {https://dblp.org/rec/conf/iros/PetersMUCNS05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/iros/NakanishiCMPS05, author = {Jun Nakanishi and Rick Cory and Michael N. Mistry and Jan Peters and Stefan Schaal}, title = {Comparative experiments on task space control with redundancy resolution}, booktitle = {2005 {IEEE/RSJ} International Conference on Intelligent Robots and Systems, Edmonton, Alberta, Canada, August 2-6, 2005}, pages = {3901--3908}, publisher = {{IEEE}}, year = {2005}, url = {https://doi.org/10.1109/IROS.2005.1545203}, doi = {10.1109/IROS.2005.1545203}, timestamp = {Thu, 18 Jul 2019 01:00:00 +0200}, biburl = {https://dblp.org/rec/conf/iros/NakanishiCMPS05.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@inproceedings{DBLP:conf/isrr/SchaalPNI03, author = {Stefan Schaal and Jan Peters and Jun Nakanishi and Auke Jan Ijspeert}, editor = {Paolo Dario and Raja Chatila}, title = {Learning Movement Primitives}, booktitle = {Robotics Research, The Eleventh International Symposium, ISRR, October 19-22, 2003, Siena, Italy}, series = {Springer Tracts in Advanced Robotics}, volume = {15}, pages = {561--572}, publisher = {Springer}, year = {2003}, url = {https://doi.org/10.1007/11008941\_60}, doi = {10.1007/11008941\_60}, timestamp = {Sat, 14 Sep 2019 14:06:07 +0200}, biburl = {https://dblp.org/rec/conf/isrr/SchaalPNI03.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
@article{DBLP:journals/apin/PetersS02, author = {Jan Peters and Patrick van der Smagt}, title = {Searching a Scalable Approach to Cerebellar Based Control}, journal = {Appl. Intell.}, volume = {17}, number = {1}, pages = {11--33}, year = {2002}, url = {https://doi.org/10.1023/A:1015775631060}, doi = {10.1023/A:1015775631060}, timestamp = {Fri, 16 Jul 2021 01:00:00 +0200}, biburl = {https://dblp.org/rec/journals/apin/PetersS02.bib}, bibsource = {dblp computer science bibliography, https://dblp.org} }
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.