Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDBibTeX records: Shie Mannor
@inproceedings{DBLP:conf/aaai/GadotDKELM24,
author = {Uri Gadot and
Esther Derman and
Navdeep Kumar and
Maxence Mohamed Elfatihi and
Kfir Levy and
Shie Mannor},
editor = {Michael J. Wooldridge and
Jennifer G. Dy and
Sriraam Natarajan},
title = {Solving Non-rectangular Reward-Robust MDPs via Frequency Regularization},
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 = {21090--21098},
publisher = {{AAAI} Press},
year = {2024},
url = {https://doi.org/10.1609/aaai.v38i19.30101},
doi = {10.1609/AAAI.V38I19.30101},
timestamp = {Tue, 02 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/GadotDKELM24.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-05643,
author = {Lior Cohen and
Kaixin Wang and
Bingyi Kang and
Shie Mannor},
title = {Improving Token-Based World Models with Parallel Observation Prediction},
journal = {CoRR},
volume = {abs/2402.05643},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.05643},
doi = {10.48550/ARXIV.2402.05643},
eprinttype = {arXiv},
eprint = {2402.05643},
timestamp = {Wed, 14 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-05643.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-05950,
author = {Nitsan Soffair and
Dotan Di Castro and
Orly Avner and
Shie Mannor},
title = {{SQT} - std Q-target},
journal = {CoRR},
volume = {abs/2402.05950},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.05950},
doi = {10.48550/ARXIV.2402.05950},
eprinttype = {arXiv},
eprint = {2402.05950},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-05950.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-05951,
author = {Nitsan Soffair and
Shie Mannor},
title = {MinMaxMin Q-learning},
journal = {CoRR},
volume = {abs/2402.05951},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.05951},
doi = {10.48550/ARXIV.2402.05951},
eprinttype = {arXiv},
eprint = {2402.05951},
timestamp = {Fri, 16 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-05951.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2402-10342,
author = {Yihan Du and
Anna Winnicki and
Gal Dalal and
Shie Mannor and
R. Srikant},
title = {Exploration-Driven Policy Optimization in {RLHF:} Theoretical Insights
on Efficient Data Utilization},
journal = {CoRR},
volume = {abs/2402.10342},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2402.10342},
doi = {10.48550/ARXIV.2402.10342},
eprinttype = {arXiv},
eprint = {2402.10342},
timestamp = {Mon, 26 Feb 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2402-10342.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-05732,
author = {Nitsan Soffair and
Shie Mannor},
title = {Conservative {DDPG} - Pessimistic {RL} without Ensemble},
journal = {CoRR},
volume = {abs/2403.05732},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.05732},
doi = {10.48550/ARXIV.2403.05732},
eprinttype = {arXiv},
eprint = {2403.05732},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-05732.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2403-06806,
author = {Navdeep Kumar and
Yashaswini Murthy and
Itai Shufaro and
Kfir Y. Levy and
R. Srikant and
Shie Mannor},
title = {On the Global Convergence of Policy Gradient in Average Reward Markov
Decision Processes},
journal = {CoRR},
volume = {abs/2403.06806},
year = {2024},
url = {https://doi.org/10.48550/arXiv.2403.06806},
doi = {10.48550/ARXIV.2403.06806},
eprinttype = {arXiv},
eprint = {2403.06806},
timestamp = {Thu, 04 Apr 2024 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2403-06806.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}
}
@inproceedings{DBLP:conf/aaai/0002HMCD23,
author = {Aviv Rosenberg and
Assaf Hallak and
Shie Mannor and
Gal Chechik and
Gal Dalal},
editor = {Brian Williams and
Yiling Chen and
Jennifer Neville},
title = {Planning and Learning with Adaptive Lookahead},
booktitle = {Thirty-Seventh {AAAI} Conference on Artificial Intelligence, {AAAI}
2023, Thirty-Fifth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2023, Thirteenth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2023, Washington, DC, USA, February
7-14, 2023},
pages = {9606--9613},
publisher = {{AAAI} Press},
year = {2023},
url = {https://doi.org/10.1609/aaai.v37i8.26149},
doi = {10.1609/AAAI.V37I8.26149},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/0002HMCD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/KhannaTMMT23,
author = {Pranav Khanna and
Guy Tennenholtz and
Nadav Merlis and
Shie Mannor and
Chen Tessler},
editor = {Noa Agmon and
Bo An and
Alessandro Ricci and
William Yeoh},
title = {Never Worse, Mostly Better: Stable Policy Improvement in Deep Reinforcement
Learning},
booktitle = {Proceedings of the 2023 International Conference on Autonomous Agents
and Multiagent Systems, {AAMAS} 2023, London, United Kingdom, 29 May
2023 - 2 June 2023},
pages = {2430--2432},
publisher = {{ACM}},
year = {2023},
url = {https://dl.acm.org/doi/10.5555/3545946.3598957},
doi = {10.5555/3545946.3598957},
timestamp = {Tue, 23 May 2023 14:27:14 +0200},
biburl = {https://dblp.org/rec/conf/atal/KhannaTMMT23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ccgrid/FuhrerSTMCZD23,
author = {Benjamin Fuhrer and
Yuval Shpigelman and
Chen Tessler and
Shie Mannor and
Gal Chechik and
Eitan Zahavi and
Gal Dalal},
editor = {Yogesh Simmhan and
Ilkay Altintas and
Ana Lucia Varbanescu and
Pavan Balaji and
Abhinandan S. Prasad and
Lorenzo Carnevale},
title = {Implementing Reinforcement Learning Datacenter Congestion Control
in {NVIDIA} NICs},
booktitle = {23rd {IEEE/ACM} International Symposium on Cluster, Cloud and Internet
Computing, CCGrid 2023, Bangalore, India, May 1-4, 2023},
pages = {331--343},
publisher = {{IEEE}},
year = {2023},
url = {https://doi.org/10.1109/CCGrid57682.2023.00039},
doi = {10.1109/CCGRID57682.2023.00039},
timestamp = {Fri, 21 Jul 2023 22:25:52 +0200},
biburl = {https://dblp.org/rec/conf/ccgrid/FuhrerSTMCZD23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AtzmonMMC23,
author = {Yuval Atzmon and
Eli A. Meirom and
Shie Mannor and
Gal Chechik},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Learning to Initiate and Reason in Event-Driven Cascading Processes},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {1218--1243},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/atzmon23a.html},
timestamp = {Mon, 28 Aug 2023 17:23:08 +0200},
biburl = {https://dblp.org/rec/conf/icml/AtzmonMMC23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KwonECM23,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Reward-Mixing MDPs with Few Latent Contexts are Learnable},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {18057--18082},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/kwon23b.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KwonECM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/NabatiTM23,
author = {Ofir Nabati and
Guy Tennenholtz and
Shie Mannor},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Representation-Driven Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {25588--25603},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/nabati23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/NabatiTM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/PeretsKM23,
author = {Binyamin Perets and
Mark Kozdoba and
Shie Mannor},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {Learning Hidden Markov Models When the Locations of Missing Observations
are Unknown},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {27642--27667},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/perets23a.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/PeretsKM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangZFM23,
author = {Kaixin Wang and
Daquan Zhou and
Jiashi Feng and
Shie Mannor},
editor = {Andreas Krause and
Emma Brunskill and
Kyunghyun Cho and
Barbara Engelhardt and
Sivan Sabato and
Jonathan Scarlett},
title = {{PPG} Reloaded: An Empirical Study on What Matters in Phasic Policy
Gradient},
booktitle = {International Conference on Machine Learning, {ICML} 2023, 23-29 July
2023, Honolulu, Hawaii, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {202},
pages = {36694--36713},
publisher = {{PMLR}},
year = {2023},
url = {https://proceedings.mlr.press/v202/wang23aw.html},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WangZFM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BelogolovskyGEM23,
author = {Stav Belogolovsky and
Ido Greenberg and
Danny Eytan and
Shie Mannor},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Individualized Dosing Dynamics via Neural Eigen Decomposition},
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/afc9f18089928eca34c347fee4757f72-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BelogolovskyGEM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GreenbergMCM23,
author = {Ido Greenberg and
Shie Mannor and
Gal Chechik and
Eli A. Meirom},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Train Hard, Fight Easy: Robust Meta Reinforcement Learning},
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/d74e6bfe9ce029526e69db14d2c281ec-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GreenbergMCM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GreenbergYM23,
author = {Ido Greenberg and
Netanel Yannay and
Shie Mannor},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Optimization or Architecture: How to Hack Kalman Filtering},
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/9dfcc83c01e94d02c751c47517855c9f-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GreenbergYM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KumarDGLM23,
author = {Navdeep Kumar and
Esther Derman and
Matthieu Geist and
Kfir Y. Levy and
Shie Mannor},
editor = {Alice Oh and
Tristan Naumann and
Amir Globerson and
Kate Saenko and
Moritz Hardt and
Sergey Levine},
title = {Policy Gradient for Rectangular Robust Markov Decision Processes},
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/ba8aee784ffe0813890288b334444eda-Abstract-Conference.html},
timestamp = {Fri, 01 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KumarDGLM23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/siggraph/TesslerKGMCP23,
author = {Chen Tessler and
Yoni Kasten and
Yunrong Guo and
Shie Mannor and
Gal Chechik and
Xue Bin Peng},
editor = {Erik Brunvand and
Alla Sheffer and
Michael Wimmer},
title = {{CALM:} Conditional Adversarial Latent Models for Directable Virtual
Characters},
booktitle = {{ACM} {SIGGRAPH} 2023 Conference Proceedings, {SIGGRAPH} 2023, Los
Angeles, CA, USA, August 6-10, 2023},
pages = {37:1--37:9},
publisher = {{ACM}},
year = {2023},
url = {https://doi.org/10.1145/3588432.3591541},
doi = {10.1145/3588432.3591541},
timestamp = {Sat, 05 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/siggraph/TesslerKGMCP23.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-01320,
author = {Shie Mannor and
Aviv Tamar},
title = {Towards Deployable {RL} - What's Broken with {RL} Research and a Potential
Fix},
journal = {CoRR},
volume = {abs/2301.01320},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.01320},
doi = {10.48550/ARXIV.2301.01320},
eprinttype = {arXiv},
eprint = {2301.01320},
timestamp = {Tue, 10 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-01320.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-11147,
author = {Ido Greenberg and
Shie Mannor and
Gal Chechik and
Eli A. Meirom},
title = {Train Hard, Fight Easy: Robust Meta Reinforcement Learning},
journal = {CoRR},
volume = {abs/2301.11147},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.11147},
doi = {10.48550/ARXIV.2301.11147},
eprinttype = {arXiv},
eprint = {2301.11147},
timestamp = {Tue, 31 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-11147.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13236,
author = {Gal Dalal and
Assaf Hallak and
Gugan Thoppe and
Shie Mannor and
Gal Chechik},
title = {SoftTreeMax: Exponential Variance Reduction in Policy Gradient via
Tree Search},
journal = {CoRR},
volume = {abs/2301.13236},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13236},
doi = {10.48550/ARXIV.2301.13236},
eprinttype = {arXiv},
eprint = {2301.13236},
timestamp = {Thu, 02 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13589,
author = {Navdeep Kumar and
Esther Derman and
Matthieu Geist and
Kfir Levy and
Shie Mannor},
title = {Policy Gradient for s-Rectangular Robust Markov Decision Processes},
journal = {CoRR},
volume = {abs/2301.13589},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13589},
doi = {10.48550/ARXIV.2301.13589},
eprinttype = {arXiv},
eprint = {2301.13589},
timestamp = {Thu, 02 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13589.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2301-13642,
author = {Navdeep Kumar and
Kfir Levy and
Kaixin Wang and
Shie Mannor},
title = {An Efficient Solution to s-Rectangular Robust Markov Decision Processes},
journal = {CoRR},
volume = {abs/2301.13642},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2301.13642},
doi = {10.48550/ARXIV.2301.13642},
eprinttype = {arXiv},
eprint = {2301.13642},
timestamp = {Thu, 02 Feb 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2301-13642.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2303-06654,
author = {Esther Derman and
Yevgeniy Men and
Matthieu Geist and
Shie Mannor},
title = {Twice Regularized Markov Decision Processes: The Equivalence between
Robustness and Regularization},
journal = {CoRR},
volume = {abs/2303.06654},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2303.06654},
doi = {10.48550/ARXIV.2303.06654},
eprinttype = {arXiv},
eprint = {2303.06654},
timestamp = {Thu, 16 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2303-06654.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-02195,
author = {Chen Tessler and
Yoni Kasten and
Yunrong Guo and
Shie Mannor and
Gal Chechik and
Xue Bin Peng},
title = {{CALM:} Conditional Adversarial Latent Models for Directable Virtual
Characters},
journal = {CoRR},
volume = {abs/2305.02195},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.02195},
doi = {10.48550/ARXIV.2305.02195},
eprinttype = {arXiv},
eprint = {2305.02195},
timestamp = {Fri, 05 May 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-02195.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-19922,
author = {Ofir Nabati and
Guy Tennenholtz and
Shie Mannor},
title = {Representation-Driven Reinforcement Learning},
journal = {CoRR},
volume = {abs/2305.19922},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2305.19922},
doi = {10.48550/ARXIV.2305.19922},
eprinttype = {arXiv},
eprint = {2305.19922},
timestamp = {Wed, 07 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2305-19922.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-05859,
author = {Kaixin Wang and
Uri Gadot and
Navdeep Kumar and
Kfir Levy and
Shie Mannor},
title = {Robust Reinforcement Learning via Adversarial Kernel Approximation},
journal = {CoRR},
volume = {abs/2306.05859},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.05859},
doi = {10.48550/ARXIV.2306.05859},
eprinttype = {arXiv},
eprint = {2306.05859},
timestamp = {Wed, 14 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-05859.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2306-14020,
author = {Stav Belogolovsky and
Ido Greenberg and
Danny Eytan and
Shie Mannor},
title = {Individualized Dosing Dynamics via Neural Eigen Decomposition},
journal = {CoRR},
volume = {abs/2306.14020},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2306.14020},
doi = {10.48550/ARXIV.2306.14020},
eprinttype = {arXiv},
eprint = {2306.14020},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2306-14020.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2307-13763,
author = {Mark Kozdoba and
Binyamin Perets and
Shie Mannor},
title = {Implicitly Normalized Explicitly Regularized Density Estimation},
journal = {CoRR},
volume = {abs/2307.13763},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2307.13763},
doi = {10.48550/ARXIV.2307.13763},
eprinttype = {arXiv},
eprint = {2307.13763},
timestamp = {Tue, 01 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2307-13763.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2309-01107,
author = {Uri Gadot and
Esther Derman and
Navdeep Kumar and
Maxence Mohamed Elfatihi and
Kfir Levy and
Shie Mannor},
title = {Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization},
journal = {CoRR},
volume = {abs/2309.01107},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2309.01107},
doi = {10.48550/ARXIV.2309.01107},
eprinttype = {arXiv},
eprint = {2309.01107},
timestamp = {Mon, 11 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2309-01107.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-00675,
author = {Ido Greenberg and
Netanel Yannay and
Shie Mannor},
title = {Optimization or Architecture: How to Hack Kalman Filtering},
journal = {CoRR},
volume = {abs/2310.00675},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.00675},
doi = {10.48550/ARXIV.2310.00675},
eprinttype = {arXiv},
eprint = {2310.00675},
timestamp = {Wed, 18 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-00675.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2310-07596,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Shie Mannor and
Constantine Caramanis},
title = {Prospective Side Information for Latent MDPs},
journal = {CoRR},
volume = {abs/2310.07596},
year = {2023},
url = {https://doi.org/10.48550/arXiv.2310.07596},
doi = {10.48550/ARXIV.2310.07596},
eprinttype = {arXiv},
eprint = {2310.07596},
timestamp = {Tue, 24 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2310-07596.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/sigmetrics/TesslerSDMKFCM22,
author = {Chen Tessler and
Yuval Shpigelman and
Gal Dalal and
Amit Mandelbaum and
Doron Haritan Kazakov and
Benjamin Fuhrer and
Gal Chechik and
Shie Mannor},
title = {Reinforcement Learning for Datacenter Congestion Control},
journal = {{SIGMETRICS} Perform. Evaluation Rev.},
volume = {49},
number = {2},
pages = {43--46},
year = {2022},
url = {https://doi.org/10.1145/3512798.3512815},
doi = {10.1145/3512798.3512815},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/sigmetrics/TesslerSDMKFCM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ShaniZM22,
author = {Lior Shani and
Tom Zahavy and
Shie Mannor},
title = {Online Apprenticeship Learning},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {8240--8248},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i8.20798},
doi = {10.1609/AAAI.V36I8.20798},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ShaniZM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZoharMT22,
author = {Roy Zohar and
Shie Mannor and
Guy Tennenholtz},
title = {Locality Matters: {A} Scalable Value Decomposition Approach for Cooperative
Multi-Agent Reinforcement Learning},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {9278--9285},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i8.20915},
doi = {10.1609/AAAI.V36I8.20915},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZoharMT22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TesslerSDMKFCM22,
author = {Chen Tessler and
Yuval Shpigelman and
Gal Dalal and
Amit Mandelbaum and
Doron Haritan Kazakov and
Benjamin Fuhrer and
Gal Chechik and
Shie Mannor},
title = {Reinforcement Learning for Datacenter Congestion Control},
booktitle = {Thirty-Sixth {AAAI} Conference on Artificial Intelligence, {AAAI}
2022, Thirty-Fourth Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2022, The Twelveth Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2022 Virtual Event, February 22
- March 1, 2022},
pages = {12615--12621},
publisher = {{AAAI} Press},
year = {2022},
url = {https://doi.org/10.1609/aaai.v36i11.21535},
doi = {10.1609/AAAI.V36I11.21535},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TesslerSDMKFCM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/corl/KarkusIM022,
author = {P{\'{e}}ter Karkus and
Boris Ivanovic and
Shie Mannor and
Marco Pavone},
editor = {Karen Liu and
Dana Kulic and
Jeffrey Ichnowski},
title = {DiffStack: {A} Differentiable and Modular Control Stack for Autonomous
Vehicles},
booktitle = {Conference on Robot Learning, CoRL 2022, 14-18 December 2022, Auckland,
New Zealand},
series = {Proceedings of Machine Learning Research},
volume = {205},
pages = {2170--2180},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v205/karkus23a.html},
timestamp = {Wed, 15 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/corl/KarkusIM022.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icinco/Mannor22,
author = {Shie Mannor},
editor = {Giuseppina Gini and
Henk Nijmeijer and
Wolfram Burgard and
Dimitar P. Filev},
title = {Reinforcement Learning for Extended Intelligence},
booktitle = {Proceedings of the 19th International Conference on Informatics in
Control, Automation and Robotics, {ICINCO} 2022, Lisbon, Portugal,
July 14-16, 2022},
pages = {5},
publisher = {{SCITEPRESS}},
year = {2022},
timestamp = {Wed, 07 Jun 2023 09:12:13 +0200},
biburl = {https://dblp.org/rec/conf/icinco/Mannor22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/TennenholtzHDMC22,
author = {Guy Tennenholtz and
Assaf Hallak and
Gal Dalal and
Shie Mannor and
Gal Chechik and
Uri Shalit},
title = {On Covariate Shift of Latent Confounders in Imitation and 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=w01vBAcewNX},
timestamp = {Sat, 20 Aug 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/TennenholtzHDMC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ShashuaMC22,
author = {Shirli Di{-}Castro Shashua and
Shie Mannor and
Dotan Di Castro},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Analysis of Stochastic Processes through Replay Buffers},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {5039--5060},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/di-castro22a.html},
timestamp = {Tue, 12 Jul 2022 17:36:52 +0200},
biburl = {https://dblp.org/rec/conf/icml/ShashuaMC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KwonECM22,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Coordinated Attacks against Contextual Bandits: Fundamental Limits
and Defense Mechanisms},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {11772--11789},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/kwon22a.html},
timestamp = {Tue, 12 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KwonECM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MeiromMMC22,
author = {Eli A. Meirom and
Haggai Maron and
Shie Mannor and
Gal Chechik},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Optimizing Tensor Network Contraction Using Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {15278--15292},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/meirom22a.html},
timestamp = {Tue, 12 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MeiromMMC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangKZHFM22,
author = {Kaixin Wang and
Navdeep Kumar and
Kuangqi Zhou and
Bryan Hooi and
Jiashi Feng and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {The Geometry of Robust Value Functions},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {22727--22751},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/wang22k.html},
timestamp = {Tue, 12 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/WangKZHFM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZakiMGM22,
author = {Mohammadi Zaki and
Avi Mohan and
Aditya Gopalan and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Stefanie Jegelka and
Le Song and
Csaba Szepesv{\'{a}}ri and
Gang Niu and
Sivan Sabato},
title = {Actor-Critic based Improper Reinforcement Learning},
booktitle = {International Conference on Machine Learning, {ICML} 2022, 17-23 July
2022, Baltimore, Maryland, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {162},
pages = {25867--25919},
publisher = {{PMLR}},
year = {2022},
url = {https://proceedings.mlr.press/v162/zaki22a.html},
timestamp = {Tue, 12 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZakiMGM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/GreenbergCGM22,
author = {Ido Greenberg and
Yinlam Chow and
Mohammad Ghavamzadeh and
Shie Mannor},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Efficient Risk-Averse Reinforcement Learning},
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/d2511dfb731fa336739782ba825cd98c-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/GreenbergCGM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KozdobaMMC22,
author = {Mark Kozdoba and
Edward Moroshko and
Shie Mannor and
Yacov Crammer},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Finite Sample Analysis Of Dynamic Regression Parameter Learning},
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/9a0c3a83cadca7c5a7355074ae5a7569-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KozdobaMMC22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KwonECM22,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Tractable Optimality in Episodic Latent MABs},
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/95a6fcdc0c8458baa9c6e14736a644f8-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KwonECM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TennenholtzM22,
author = {Guy Tennenholtz and
Shie Mannor},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Uncertainty Estimation Using Riemannian Model Dynamics for Offline
Reinforcement Learning},
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/78e36c70d5051e9e271b00289624d709-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TennenholtzM22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TennenholtzMSMS22,
author = {Guy Tennenholtz and
Nadav Merlis and
Lior Shani and
Shie Mannor and
Uri Shalit and
Gal Chechik and
Assaf Hallak and
Gal Dalal},
editor = {Sanmi Koyejo and
S. Mohamed and
A. Agarwal and
Danielle Belgrave and
K. Cho and
A. Oh},
title = {Reinforcement Learning with a Terminator},
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/e83b86156555ab9692743f9f8f67adf1-Abstract-Conference.html},
timestamp = {Mon, 08 Jan 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TennenholtzMSMS22.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-12403,
author = {Aviv Rosenberg and
Assaf Hallak and
Shie Mannor and
Gal Chechik and
Gal Dalal},
title = {Planning and Learning with Adaptive Lookahead},
journal = {CoRR},
volume = {abs/2201.12403},
year = {2022},
url = {https://arxiv.org/abs/2201.12403},
eprinttype = {arXiv},
eprint = {2201.12403},
timestamp = {Wed, 02 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-12403.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-12700,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
title = {Coordinated Attacks against Contextual Bandits: Fundamental Limits
and Defense Mechanisms},
journal = {CoRR},
volume = {abs/2201.12700},
year = {2022},
url = {https://arxiv.org/abs/2201.12700},
eprinttype = {arXiv},
eprint = {2201.12700},
timestamp = {Wed, 02 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-12700.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2201-12929,
author = {Kaixin Wang and
Navdeep Kumar and
Kuangqi Zhou and
Bryan Hooi and
Jiashi Feng and
Shie Mannor},
title = {The Geometry of Robust Value Functions},
journal = {CoRR},
volume = {abs/2201.12929},
year = {2022},
url = {https://arxiv.org/abs/2201.12929},
eprinttype = {arXiv},
eprint = {2201.12929},
timestamp = {Wed, 02 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2201-12929.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-00117,
author = {Stav Belogolovsky and
Ido Greenberg and
Danny Eytan and
Shie Mannor},
title = {Continuous Forecasting via Neural Eigen Decomposition of Stochastic
Dynamics},
journal = {CoRR},
volume = {abs/2202.00117},
year = {2022},
url = {https://arxiv.org/abs/2202.00117},
eprinttype = {arXiv},
eprint = {2202.00117},
timestamp = {Tue, 27 Jun 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-00117.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-01108,
author = {Yuval Atzmon and
Eli A. Meirom and
Shie Mannor and
Gal Chechik},
title = {Learning to reason about and to act on physical cascading events},
journal = {CoRR},
volume = {abs/2202.01108},
year = {2022},
url = {https://arxiv.org/abs/2202.01108},
eprinttype = {arXiv},
eprint = {2202.01108},
timestamp = {Wed, 09 Feb 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2202-01108.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2203-06527,
author = {Binyamin Perets and
Mark Kozdoba and
Shie Mannor},
title = {Whats Missing? Learning Hidden Markov Models When the Locations of
Missing Observations are Unknown},
journal = {CoRR},
volume = {abs/2203.06527},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2203.06527},
doi = {10.48550/ARXIV.2203.06527},
eprinttype = {arXiv},
eprint = {2203.06527},
timestamp = {Wed, 16 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2203-06527.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2204-09052,
author = {Eli A. Meirom and
Haggai Maron and
Shie Mannor and
Gal Chechik},
title = {Optimizing Tensor Network Contraction Using Reinforcement Learning},
journal = {CoRR},
volume = {abs/2204.09052},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2204.09052},
doi = {10.48550/ARXIV.2204.09052},
eprinttype = {arXiv},
eprint = {2204.09052},
timestamp = {Mon, 25 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2204-09052.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-05138,
author = {Ido Greenberg and
Yinlam Chow and
Mohammad Ghavamzadeh and
Shie Mannor},
title = {Efficient Risk-Averse Reinforcement Learning},
journal = {CoRR},
volume = {abs/2205.05138},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.05138},
doi = {10.48550/ARXIV.2205.05138},
eprinttype = {arXiv},
eprint = {2205.05138},
timestamp = {Tue, 17 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-05138.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-14327,
author = {Navdeep Kumar and
Kfir Levy and
Kaixin Wang and
Shie Mannor},
title = {Efficient Policy Iteration for Robust Markov Decision Processes via
Regularization},
journal = {CoRR},
volume = {abs/2205.14327},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.14327},
doi = {10.48550/ARXIV.2205.14327},
eprinttype = {arXiv},
eprint = {2205.14327},
timestamp = {Fri, 22 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-14327.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-15376,
author = {Guy Tennenholtz and
Nadav Merlis and
Lior Shani and
Shie Mannor and
Uri Shalit and
Gal Chechik and
Assaf Hallak and
Gal Dalal},
title = {Reinforcement Learning with a Terminator},
journal = {CoRR},
volume = {abs/2205.15376},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2205.15376},
doi = {10.48550/ARXIV.2205.15376},
eprinttype = {arXiv},
eprint = {2205.15376},
timestamp = {Wed, 01 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2205-15376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2206-12848,
author = {Shirli Di{-}Castro Shashua and
Shie Mannor and
Dotan Di Castro},
title = {Analysis of Stochastic Processes through Replay Buffers},
journal = {CoRR},
volume = {abs/2206.12848},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2206.12848},
doi = {10.48550/ARXIV.2206.12848},
eprinttype = {arXiv},
eprint = {2206.12848},
timestamp = {Mon, 04 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2206-12848.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-02295,
author = {Benjamin Fuhrer and
Yuval Shpigelman and
Chen Tessler and
Shie Mannor and
Gal Chechik and
Eitan Zahavi and
Gal Dalal},
title = {Implementing Reinforcement Learning Datacenter Congestion Control
in {NVIDIA} NICs},
journal = {CoRR},
volume = {abs/2207.02295},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.02295},
doi = {10.48550/ARXIV.2207.02295},
eprinttype = {arXiv},
eprint = {2207.02295},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-02295.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-09090,
author = {Mohammadi Zaki and
Avinash Mohan and
Aditya Gopalan and
Shie Mannor},
title = {Actor-Critic based Improper Reinforcement Learning},
journal = {CoRR},
volume = {abs/2207.09090},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2207.09090},
doi = {10.48550/ARXIV.2207.09090},
eprinttype = {arXiv},
eprint = {2207.09090},
timestamp = {Mon, 25 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2207-09090.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2209-13966,
author = {Gal Dalal and
Assaf Hallak and
Shie Mannor and
Gal Chechik},
title = {SoftTreeMax: Policy Gradient with Tree Search},
journal = {CoRR},
volume = {abs/2209.13966},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2209.13966},
doi = {10.48550/ARXIV.2209.13966},
eprinttype = {arXiv},
eprint = {2209.13966},
timestamp = {Thu, 06 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2209-13966.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-00991,
author = {Navdeep Kumar and
Kaixin Wang and
Kfir Levy and
Shie Mannor},
title = {Policy Gradient for Reinforcement Learning with General Utilities},
journal = {CoRR},
volume = {abs/2210.00991},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.00991},
doi = {10.48550/ARXIV.2210.00991},
eprinttype = {arXiv},
eprint = {2210.00991},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-00991.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-02594,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
title = {Reward-Mixing MDPs with a Few Latent Contexts are Learnable},
journal = {CoRR},
volume = {abs/2210.02594},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.02594},
doi = {10.48550/ARXIV.2210.02594},
eprinttype = {arXiv},
eprint = {2210.02594},
timestamp = {Fri, 07 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-02594.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2210-03528,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
title = {Tractable Optimality in Episodic Latent MABs},
journal = {CoRR},
volume = {abs/2210.03528},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2210.03528},
doi = {10.48550/ARXIV.2210.03528},
eprinttype = {arXiv},
eprint = {2210.03528},
timestamp = {Wed, 12 Oct 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2210-03528.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-06437,
author = {P{\'{e}}ter Karkus and
Boris Ivanovic and
Shie Mannor and
Marco Pavone},
title = {DiffStack: {A} Differentiable and Modular Control Stack for Autonomous
Vehicles},
journal = {CoRR},
volume = {abs/2212.06437},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.06437},
doi = {10.48550/ARXIV.2212.06437},
eprinttype = {arXiv},
eprint = {2212.06437},
timestamp = {Mon, 02 Jan 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-06437.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/BelogolovskyKMT21,
author = {Stav Belogolovsky and
Philip Korsunsky and
Shie Mannor and
Chen Tessler and
Tom Zahavy},
title = {Inverse reinforcement learning in contextual MDPs},
journal = {Mach. Learn.},
volume = {110},
number = {9},
pages = {2295--2334},
year = {2021},
url = {https://doi.org/10.1007/s10994-021-05984-x},
doi = {10.1007/S10994-021-05984-X},
timestamp = {Sun, 06 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/BelogolovskyKMT21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/EfroniMM21,
author = {Yonathan Efroni and
Nadav Merlis and
Shie Mannor},
title = {Reinforcement Learning with Trajectory Feedback},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {7288--7295},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i8.16895},
doi = {10.1609/AAAI.V35I8.16895},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/EfroniMM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/MerlisM21,
author = {Nadav Merlis and
Shie Mannor},
title = {Lenient Regret for Multi-Armed Bandits},
booktitle = {Thirty-Fifth {AAAI} Conference on Artificial Intelligence, {AAAI}
2021, Thirty-Third Conference on Innovative Applications of Artificial
Intelligence, {IAAI} 2021, The Eleventh Symposium on Educational Advances
in Artificial Intelligence, {EAAI} 2021, Virtual Event, February 2-9,
2021},
pages = {8950--8957},
publisher = {{AAAI} Press},
year = {2021},
url = {https://doi.org/10.1609/aaai.v35i10.17082},
doi = {10.1609/AAAI.V35I10.17082},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/MerlisM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amcc/MohanMK21,
author = {Avi Mohan and
Shie Mannor and
Arman C. Kizilkale},
title = {On the Volatility of Optimal Control Policies of a Class of Linear
Quadratic Regulators},
booktitle = {2021 American Control Conference, {ACC} 2021, New Orleans, LA, USA,
May 25-28, 2021},
pages = {4533--4540},
publisher = {{IEEE}},
year = {2021},
url = {https://doi.org/10.23919/ACC50511.2021.9482645},
doi = {10.23919/ACC50511.2021.9482645},
timestamp = {Fri, 30 Jul 2021 11:11:12 +0200},
biburl = {https://dblp.org/rec/conf/amcc/MohanMK21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cvpr/PonyNM21,
author = {Roi Pony and
Itay Naeh and
Shie Mannor},
title = {Over-the-Air Adversarial Flickering Attacks Against Video Recognition
Networks},
booktitle = {{IEEE} Conference on Computer Vision and Pattern Recognition, {CVPR}
2021, virtual, June 19-25, 2021},
pages = {515--524},
publisher = {Computer Vision Foundation / {IEEE}},
year = {2021},
url = {https://openaccess.thecvf.com/content/CVPR2021/html/Pony\_Over-the-Air\_Adversarial\_Flickering\_Attacks\_Against\_Video\_Recognition\_Networks\_CVPR\_2021\_paper.html},
doi = {10.1109/CVPR46437.2021.00058},
timestamp = {Mon, 18 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cvpr/PonyNM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/DermanDM21,
author = {Esther Derman and
Gal Dalal and
Shie Mannor},
title = {Acting in Delayed Environments with Non-Stationary Markov Policies},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=j1RMMKeP2gR},
timestamp = {Wed, 23 Jun 2021 17:36:39 +0200},
biburl = {https://dblp.org/rec/conf/iclr/DermanDM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/KhadkaAMBMMHTM21,
author = {Shauharda Khadka and
Estelle Aflalo and
Mattias Marder and
Avrech Ben{-}David and
Santiago Miret and
Shie Mannor and
Tamir Hazan and
Hanlin Tang and
Somdeb Majumdar},
title = {Optimizing Memory Placement using Evolutionary Graph Reinforcement
Learning},
booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
Virtual Event, Austria, May 3-7, 2021},
publisher = {OpenReview.net},
year = {2021},
url = {https://openreview.net/forum?id=-6vS\_4Kfz0},
timestamp = {Wed, 23 Jun 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/iclr/KhadkaAMBMMHTM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/EfroniMSM21,
author = {Yonathan Efroni and
Nadav Merlis and
Aadirupa Saha and
Shie Mannor},
editor = {Marina Meila and
Tong Zhang},
title = {Confidence-Budget Matching for Sequential Budgeted Learning},
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 = {2937--2947},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/efroni21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/EfroniMSM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GreenbergM21,
author = {Ido Greenberg and
Shie Mannor},
editor = {Marina Meila and
Tong Zhang},
title = {Detecting Rewards Deterioration in Episodic Reinforcement Learning},
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 = {3842--3853},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/greenberg21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/GreenbergM21.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/icml/MeiromMMC21,
author = {Eli A. Meirom and
Haggai Maron and
Shie Mannor and
Gal Chechik},
editor = {Marina Meila and
Tong Zhang},
title = {Controlling Graph Dynamics with Reinforcement Learning and Graph Neural
Networks},
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 = {7565--7577},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/meirom21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MeiromMMC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/NabatiZM21,
author = {Ofir Nabati and
Tom Zahavy and
Shie Mannor},
editor = {Marina Meila and
Tong Zhang},
title = {Online Limited Memory Neural-Linear Bandits with Likelihood Matching},
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 = {7905--7915},
publisher = {{PMLR}},
year = {2021},
url = {http://proceedings.mlr.press/v139/nabati21a.html},
timestamp = {Wed, 25 Aug 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/NabatiZM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KwonECM21,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Reinforcement Learning in Reward-Mixing MDPs},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {2253--2264},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/11f9e78e4899a78dedd439fc583b6693-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KwonECM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DalalHDFMC21,
author = {Gal Dalal and
Assaf Hallak and
Steven Dalton and
Iuri Frosio and
Shie Mannor and
Gal Chechik},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Improve Agents without Retraining: Parallel Tree Search with Off-Policy
Correction},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {5518--5530},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/2bd235c31c97855b7ef2dc8b414779af-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/DalalHDFMC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ShashuaCM21,
author = {Shirli Di{-}Castro Shashua and
Dotan Di Castro and
Shie Mannor},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Sim and Real: Better Together},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {6868--6880},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/36f4d832825380f102846560a5104c90-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/ShashuaCM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/DermanGM21,
author = {Esther Derman and
Matthieu Geist and
Shie Mannor},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {Twice regularized MDPs and the equivalence between robustness and
regularization},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {22274--22287},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/bb1443cc31d7396bf73e7858cea114e1-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/DermanGM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KwonECM21a,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
editor = {Marc'Aurelio Ranzato and
Alina Beygelzimer and
Yann N. Dauphin and
Percy Liang and
Jennifer Wortman Vaughan},
title = {{RL} for Latent MDPs: Regret Guarantees and a Lower Bound},
booktitle = {Advances in Neural Information Processing Systems 34: Annual Conference
on Neural Information Processing Systems 2021, NeurIPS 2021, December
6-14, 2021, virtual},
pages = {24523--24534},
year = {2021},
url = {https://proceedings.neurips.cc/paper/2021/hash/cd755a6c6b699f3262bcc2aa46ab507e-Abstract.html},
timestamp = {Tue, 03 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/nips/KwonECM21a.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/uai/BaramTM21,
author = {Nir Baram and
Guy Tennenholtz and
Shie Mannor},
editor = {Cassio P. de Campos and
Marloes H. Maathuis and
Erik Quaeghebeur},
title = {Action redundancy in reinforcement learning},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial
Intelligence, {UAI} 2021, Virtual Event, 27-30 July 2021},
series = {Proceedings of Machine Learning Research},
volume = {161},
pages = {376--385},
publisher = {{AUAI} Press},
year = {2021},
url = {https://proceedings.mlr.press/v161/baram21a.html},
timestamp = {Fri, 17 Dec 2021 17:06:27 +0100},
biburl = {https://dblp.org/rec/conf/uai/BaramTM21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/TennenholtzSME21,
author = {Guy Tennenholtz and
Uri Shalit and
Shie Mannor and
Yonathan Efroni},
editor = {Cassio P. de Campos and
Marloes H. Maathuis and
Erik Quaeghebeur},
title = {Bandits with partially observable confounded data},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial
Intelligence, {UAI} 2021, Virtual Event, 27-30 July 2021},
series = {Proceedings of Machine Learning Research},
volume = {161},
pages = {430--439},
publisher = {{AUAI} Press},
year = {2021},
url = {https://proceedings.mlr.press/v161/tennenholtz21a.html},
timestamp = {Fri, 17 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/TennenholtzSME21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/AgrawalMAMC21,
author = {Harsh Agrawal and
Eli A. Meirom and
Yuval Atzmon and
Shie Mannor and
Gal Chechik},
editor = {Cassio P. de Campos and
Marloes H. Maathuis and
Erik Quaeghebeur},
title = {Known unknowns: Learning novel concepts using reasoning-by-elimination},
booktitle = {Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial
Intelligence, {UAI} 2021, Virtual Event, 27-30 July 2021},
series = {Proceedings of Machine Learning Research},
volume = {161},
pages = {504--514},
publisher = {{AUAI} Press},
year = {2021},
url = {https://proceedings.mlr.press/v161/agrawal21a.html},
timestamp = {Fri, 17 Dec 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/AgrawalMAMC21.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2101-11992,
author = {Esther Derman and
Gal Dalal and
Shie Mannor},
title = {Acting in Delayed Environments with Non-Stationary Markov Policies},
journal = {CoRR},
volume = {abs/2101.11992},
year = {2021},
url = {https://arxiv.org/abs/2101.11992},
eprinttype = {arXiv},
eprint = {2101.11992},
timestamp = {Sun, 31 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2101-11992.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-03400,
author = {Yonathan Efroni and
Nadav Merlis and
Aadirupa Saha and
Shie Mannor},
title = {Confidence-Budget Matching for Sequential Budgeted Learning},
journal = {CoRR},
volume = {abs/2102.03400},
year = {2021},
url = {https://arxiv.org/abs/2102.03400},
eprinttype = {arXiv},
eprint = {2102.03400},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-03400.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-03799,
author = {Ofir Nabati and
Tom Zahavy and
Shie Mannor},
title = {Online Limited Memory Neural-Linear Bandits with Likelihood Matching},
journal = {CoRR},
volume = {abs/2102.03799},
year = {2021},
url = {https://arxiv.org/abs/2102.03799},
eprinttype = {arXiv},
eprint = {2102.03799},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-03799.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-03802,
author = {Mark Kozdoba and
Shie Mannor},
title = {Dimension Free Generalization Bounds for Non Linear Metric Learning},
journal = {CoRR},
volume = {abs/2102.03802},
year = {2021},
url = {https://arxiv.org/abs/2102.03802},
eprinttype = {arXiv},
eprint = {2102.03802},
timestamp = {Wed, 10 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-03802.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-04939,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
title = {{RL} for Latent MDPs: Regret Guarantees and a Lower Bound},
journal = {CoRR},
volume = {abs/2102.04939},
year = {2021},
url = {https://arxiv.org/abs/2102.04939},
eprinttype = {arXiv},
eprint = {2102.04939},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-04939.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-06924,
author = {Lior Shani and
Tom Zahavy and
Shie Mannor},
title = {Online Apprenticeship Learning},
journal = {CoRR},
volume = {abs/2102.06924},
year = {2021},
url = {https://arxiv.org/abs/2102.06924},
eprinttype = {arXiv},
eprint = {2102.06924},
timestamp = {Thu, 18 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06924.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-08201,
author = {Mohammadi Zaki and
Avinash Mohan and
Aditya Gopalan and
Shie Mannor},
title = {Improper Learning with Gradient-based Policy Optimization},
journal = {CoRR},
volume = {abs/2102.08201},
year = {2021},
url = {https://arxiv.org/abs/2102.08201},
eprinttype = {arXiv},
eprint = {2102.08201},
timestamp = {Fri, 19 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-08201.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-09337,
author = {Chen Tessler and
Yuval Shpigelman and
Gal Dalal and
Amit Mandelbaum and
Doron Haritan Kazakov and
Benjamin Fuhrer and
Gal Chechik and
Shie Mannor},
title = {Reinforcement Learning for Datacenter Congestion Control},
journal = {CoRR},
volume = {abs/2102.09337},
year = {2021},
url = {https://arxiv.org/abs/2102.09337},
eprinttype = {arXiv},
eprint = {2102.09337},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-09337.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-11327,
author = {Guy Tennenholtz and
Nir Baram and
Shie Mannor},
title = {{GELATO:} Geometrically Enriched Latent Model for Offline Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2102.11327},
year = {2021},
url = {https://arxiv.org/abs/2102.11327},
eprinttype = {arXiv},
eprint = {2102.11327},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-11327.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2102-11329,
author = {Nir Baram and
Guy Tennenholtz and
Shie Mannor},
title = {Action Redundancy in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2102.11329},
year = {2021},
url = {https://arxiv.org/abs/2102.11329},
eprinttype = {arXiv},
eprint = {2102.11329},
timestamp = {Wed, 24 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-11329.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2103-10176,
author = {Nir Baram and
Guy Tennenholtz and
Shie Mannor},
title = {Maximum Entropy Reinforcement Learning with Mixture Policies},
journal = {CoRR},
volume = {abs/2103.10176},
year = {2021},
url = {https://arxiv.org/abs/2103.10176},
eprinttype = {arXiv},
eprint = {2103.10176},
timestamp = {Wed, 24 Mar 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2103-10176.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2104-02372,
author = {Ido Greenberg and
Shie Mannor and
Netanel Yannay},
title = {Using Kalman Filter The Right Way: Noise Estimation Is Not Optimal},
journal = {CoRR},
volume = {abs/2104.02372},
year = {2021},
url = {https://arxiv.org/abs/2104.02372},
eprinttype = {arXiv},
eprint = {2104.02372},
timestamp = {Tue, 13 Apr 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2104-02372.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-00210,
author = {Mohammadi Zaki and
Avi Mohan and
Aditya Gopalan and
Shie Mannor},
title = {Better than the Best: Gradient-based Improper Reinforcement Learning
for Network Scheduling},
journal = {CoRR},
volume = {abs/2105.00210},
year = {2021},
url = {https://arxiv.org/abs/2105.00210},
eprinttype = {arXiv},
eprint = {2105.00210},
timestamp = {Wed, 12 May 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2105-00210.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-2105-12189,
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-2107-01715,
author = {Assaf Hallak and
Gal Dalal and
Steven Dalton and
Iuri Frosio and
Shie Mannor and
Gal Chechik},
title = {Improve Agents without Retraining: Parallel Tree Search with Off-Policy
Correction},
journal = {CoRR},
volume = {abs/2107.01715},
year = {2021},
url = {https://arxiv.org/abs/2107.01715},
eprinttype = {arXiv},
eprint = {2107.01715},
timestamp = {Wed, 07 Jul 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2107-01715.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2109-10632,
author = {Roy Zohar and
Shie Mannor and
Guy Tennenholtz},
title = {Locality Matters: {A} Scalable Value Decomposition Approach for Cooperative
Multi-Agent Reinforcement Learning},
journal = {CoRR},
volume = {abs/2109.10632},
year = {2021},
url = {https://arxiv.org/abs/2109.10632},
eprinttype = {arXiv},
eprint = {2109.10632},
timestamp = {Mon, 27 Sep 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2109-10632.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-00445,
author = {Shirli Di{-}Castro Shashua and
Dotan Di Castro and
Shie Mannor},
title = {Sim and Real: Better Together},
journal = {CoRR},
volume = {abs/2110.00445},
year = {2021},
url = {https://arxiv.org/abs/2110.00445},
eprinttype = {arXiv},
eprint = {2110.00445},
timestamp = {Mon, 25 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-00445.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-2110-03743,
author = {Jeongyeol Kwon and
Yonathan Efroni and
Constantine Caramanis and
Shie Mannor},
title = {Reinforcement Learning in Reward-Mixing MDPs},
journal = {CoRR},
volume = {abs/2110.03743},
year = {2021},
url = {https://arxiv.org/abs/2110.03743},
eprinttype = {arXiv},
eprint = {2110.03743},
timestamp = {Thu, 21 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-03743.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-05724,
author = {Nadav Merlis and
Yonathan Efroni and
Shie Mannor},
title = {Dare not to Ask: Problem-Dependent Guarantees for Budgeted Bandits},
journal = {CoRR},
volume = {abs/2110.05724},
year = {2021},
url = {https://arxiv.org/abs/2110.05724},
eprinttype = {arXiv},
eprint = {2110.05724},
timestamp = {Thu, 21 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-05724.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-06267,
author = {Esther Derman and
Matthieu Geist and
Shie Mannor},
title = {Twice regularized MDPs and the equivalence between robustness and
regularization},
journal = {CoRR},
volume = {abs/2110.06267},
year = {2021},
url = {https://arxiv.org/abs/2110.06267},
eprinttype = {arXiv},
eprint = {2110.06267},
timestamp = {Fri, 22 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-06267.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-06539,
author = {Guy Tennenholtz and
Assaf Hallak and
Gal Dalal and
Shie Mannor and
Gal Chechik and
Uri Shalit},
title = {On Covariate Shift of Latent Confounders in Imitation and Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2110.06539},
year = {2021},
url = {https://arxiv.org/abs/2110.06539},
eprinttype = {arXiv},
eprint = {2110.06539},
timestamp = {Fri, 22 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-06539.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ShaniEM20,
author = {Lior Shani and
Yonathan Efroni and
Shie Mannor},
title = {Adaptive Trust Region Policy Optimization: Global Convergence and
Faster Rates for Regularized MDPs},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {5668--5675},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i04.6021},
doi = {10.1609/AAAI.V34I04.6021},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ShaniEM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TennenholtzSM20,
author = {Guy Tennenholtz and
Uri Shalit and
Shie Mannor},
title = {Off-Policy Evaluation in Partially Observable Environments},
booktitle = {The Thirty-Fourth {AAAI} Conference on Artificial Intelligence, {AAAI}
2020, The Thirty-Second Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2020, The Tenth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2020, New York, NY, USA,
February 7-12, 2020},
pages = {10276--10283},
publisher = {{AAAI} Press},
year = {2020},
url = {https://doi.org/10.1609/aaai.v34i06.6590},
doi = {10.1609/AAAI.V34I06.6590},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TennenholtzSM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/alt/FontaineMP20,
author = {Xavier Fontaine and
Shie Mannor and
Vianney Perchet},
editor = {Aryeh Kontorovich and
Gergely Neu},
title = {An adaptive stochastic optimization algorithm for resource allocation},
booktitle = {Algorithmic Learning Theory, {ALT} 2020, 8-11 February 2020, San Diego,
CA, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {117},
pages = {319--363},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v117/fontaine20a.html},
timestamp = {Thu, 18 Jun 2020 11:48:49 +0200},
biburl = {https://dblp.org/rec/conf/alt/FontaineMP20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MerlisM20,
author = {Nadav Merlis and
Shie Mannor},
editor = {Jacob D. Abernethy and
Shivani Agarwal},
title = {Tight Lower Bounds for Combinatorial Multi-Armed Bandits},
booktitle = {Conference on Learning Theory, {COLT} 2020, 9-12 July 2020, Virtual
Event [Graz, Austria]},
series = {Proceedings of Machine Learning Research},
volume = {125},
pages = {2830--2857},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v125/merlis20a.html},
timestamp = {Fri, 27 Nov 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/MerlisM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FisherKM20,
author = {Dan Fisher and
Mark Kozdoba and
Shie Mannor},
title = {Topic Modeling via Full Dependence Mixtures},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {3188--3198},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/fisher20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/FisherKM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ShaniE0M20,
author = {Lior Shani and
Yonathan Efroni and
Aviv Rosenberg and
Shie Mannor},
title = {Optimistic Policy Optimization with Bandit Feedback},
booktitle = {Proceedings of the 37th International Conference on Machine Learning,
{ICML} 2020, 13-18 July 2020, Virtual Event},
series = {Proceedings of Machine Learning Research},
volume = {119},
pages = {8604--8613},
publisher = {{PMLR}},
year = {2020},
url = {http://proceedings.mlr.press/v119/shani20a.html},
timestamp = {Tue, 15 Dec 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/ShaniE0M20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/EfroniGM20,
author = {Yonathan Efroni and
Mohammad Ghavamzadeh and
Shie Mannor},
editor = {Hugo Larochelle and
Marc'Aurelio Ranzato and
Raia Hadsell and
Maria{-}Florina Balcan and
Hsuan{-}Tien Lin},
title = {Online Planning with Lookahead Policies},
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/a18aa23ee676d7f5ffb34cf16df3e08c-Abstract.html},
timestamp = {Tue, 19 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/EfroniGM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wacv/GandhiKCMSAKOM20,
author = {Shreyansh Gandhi and
Samrat Kokkula and
Abon Chaudhuri and
Alessandro Magnani and
Theban Stanley and
Behzad Ahmadi and
Venkatesh Kandaswamy and
Omer Ovenc and
Shie Mannor},
title = {Scalable Detection of Offensive and Non-compliant Content / Logo in
Product Images},
booktitle = {{IEEE} Winter Conference on Applications of Computer Vision, {WACV}
2020, Snowmass Village, CO, USA, March 1-5, 2020},
pages = {2236--2245},
publisher = {{IEEE}},
year = {2020},
url = {https://doi.org/10.1109/WACV45572.2020.9093454},
doi = {10.1109/WACV45572.2020.9093454},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/wacv/GandhiKCMSAKOM20.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-03327,
author = {Chen Tessler and
Shie Mannor},
title = {Maximizing the Total Reward via Reward Tweaking},
journal = {CoRR},
volume = {abs/2002.03327},
year = {2020},
url = {https://arxiv.org/abs/2002.03327},
eprinttype = {arXiv},
eprint = {2002.03327},
timestamp = {Wed, 12 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-03327.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-05123,
author = {Itay Naeh and
Roi Pony and
Shie Mannor},
title = {Patternless Adversarial Attacks on Video Recognition Networks},
journal = {CoRR},
volume = {abs/2002.05123},
year = {2020},
url = {https://arxiv.org/abs/2002.05123},
eprinttype = {arXiv},
eprint = {2002.05123},
timestamp = {Fri, 14 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-05123.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-05392,
author = {Nadav Merlis and
Shie Mannor},
title = {Tight Lower Bounds for Combinatorial Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/2002.05392},
year = {2020},
url = {https://arxiv.org/abs/2002.05392},
eprinttype = {arXiv},
eprint = {2002.05392},
timestamp = {Fri, 14 Feb 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-05392.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-06808,
author = {Avinash Mohan and
Shie Mannor and
Arman C. Kizilkale},
title = {Price Volatility in Electricity Markets: {A} Stochastic Control Perspective},
journal = {CoRR},
volume = {abs/2002.06808},
year = {2020},
url = {https://arxiv.org/abs/2002.06808},
eprinttype = {arXiv},
eprint = {2002.06808},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-06808.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-07171,
author = {Shirli Di{-}Castro Shashua and
Shie Mannor},
title = {Kalman meets Bellman: Improving Policy Evaluation through Value Tracking},
journal = {CoRR},
volume = {abs/2002.07171},
year = {2020},
url = {https://arxiv.org/abs/2002.07171},
eprinttype = {arXiv},
eprint = {2002.07171},
timestamp = {Mon, 02 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-07171.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-08243,
author = {Yonathan Efroni and
Lior Shani and
Aviv Rosenberg and
Shie Mannor},
title = {Optimistic Policy Optimization with Bandit Feedback},
journal = {CoRR},
volume = {abs/2002.08243},
year = {2020},
url = {https://arxiv.org/abs/2002.08243},
eprinttype = {arXiv},
eprint = {2002.08243},
timestamp = {Thu, 05 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-08243.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2002-09864,
author = {Daniel Teitelman and
Itay Naeh and
Shie Mannor},
title = {Stealing Black-Box Functionality Using The Deep Neural Tree Architecture},
journal = {CoRR},
volume = {abs/2002.09864},
year = {2020},
url = {https://arxiv.org/abs/2002.09864},
eprinttype = {arXiv},
eprint = {2002.09864},
timestamp = {Tue, 03 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2002-09864.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-02189,
author = {Yonathan Efroni and
Shie Mannor and
Matteo Pirotta},
title = {Exploration-Exploitation in Constrained MDPs},
journal = {CoRR},
volume = {abs/2003.02189},
year = {2020},
url = {https://arxiv.org/abs/2003.02189},
eprinttype = {arXiv},
eprint = {2003.02189},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-02189.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2003-02894,
author = {Esther Derman and
Shie Mannor},
title = {Distributional Robustness and Regularization in Reinforcement Learning},
journal = {CoRR},
volume = {abs/2003.02894},
year = {2020},
url = {https://arxiv.org/abs/2003.02894},
eprinttype = {arXiv},
eprint = {2003.02894},
timestamp = {Tue, 10 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2003-02894.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-06731,
author = {Guy Tennenholtz and
Uri Shalit and
Shie Mannor and
Yonathan Efroni},
title = {Bandits with Partially Observable Offline Data},
journal = {CoRR},
volume = {abs/2006.06731},
year = {2020},
url = {https://arxiv.org/abs/2006.06731},
eprinttype = {arXiv},
eprint = {2006.06731},
timestamp = {Wed, 17 Jun 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2006-06731.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-07298,
author = {Shauharda Khadka and
Estelle Aflalo and
Mattias Marder and
Avrech Ben{-}David and
Santiago Miret and
Hanlin Tang and
Shie Mannor and
Tamir Hazan and
Somdeb Majumdar},
title = {Optimizing Memory Placement using Evolutionary Graph Reinforcement
Learning},
journal = {CoRR},
volume = {abs/2007.07298},
year = {2020},
url = {https://arxiv.org/abs/2007.07298},
eprinttype = {arXiv},
eprint = {2007.07298},
timestamp = {Tue, 21 Jul 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-07298.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2007-13232,
author = {Asaf B. Cassel and
Shie Mannor and
Guy Tennenholtz},
title = {The Pendulum Arrangement: Maximizing the Escape Time of Heterogeneous
Random Walks},
journal = {CoRR},
volume = {abs/2007.13232},
year = {2020},
url = {https://arxiv.org/abs/2007.13232},
eprinttype = {arXiv},
eprint = {2007.13232},
timestamp = {Sun, 03 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2007-13232.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-03959,
author = {Nadav Merlis and
Shie Mannor},
title = {Lenient Regret for Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/2008.03959},
year = {2020},
url = {https://arxiv.org/abs/2008.03959},
eprinttype = {arXiv},
eprint = {2008.03959},
timestamp = {Fri, 14 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-03959.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2008-06036,
author = {Yonathan Efroni and
Nadav Merlis and
Shie Mannor},
title = {Reinforcement Learning with Trajectory Feedback},
journal = {CoRR},
volume = {abs/2008.06036},
year = {2020},
url = {https://arxiv.org/abs/2008.06036},
eprinttype = {arXiv},
eprint = {2008.06036},
timestamp = {Mon, 17 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2008-06036.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-05313,
author = {Eli A. Meirom and
Haggai Maron and
Shie Mannor and
Gal Chechik},
title = {How to Stop Epidemics: Controlling Graph Dynamics with Reinforcement
Learning and Graph Neural Networks},
journal = {CoRR},
volume = {abs/2010.05313},
year = {2020},
url = {https://arxiv.org/abs/2010.05313},
eprinttype = {arXiv},
eprint = {2010.05313},
timestamp = {Tue, 20 Oct 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-05313.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-11660,
author = {Ido Greenberg and
Shie Mannor},
title = {Drift Detection in Episodic Data: Detect When Your Agent Starts Faltering},
journal = {CoRR},
volume = {abs/2010.11660},
year = {2020},
url = {https://arxiv.org/abs/2010.11660},
eprinttype = {arXiv},
eprint = {2010.11660},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2010-11660.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2012-04210,
author = {Ahmet Fatih Inci and
Evgeny Bolotin and
Yaosheng Fu and
Gal Dalal and
Shie Mannor and
David W. Nellans and
Diana Marculescu},
title = {The Architectural Implications of Distributed Reinforcement Learning
on {CPU-GPU} Systems},
journal = {CoRR},
volume = {abs/2012.04210},
year = {2020},
url = {https://arxiv.org/abs/2012.04210},
eprinttype = {arXiv},
eprint = {2012.04210},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2012-04210.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ton/AvnerM19,
author = {Orly Avner and
Shie Mannor},
title = {Multi-User Communication Networks: {A} Coordinated Multi-Armed Bandit
Approach},
journal = {{IEEE/ACM} Trans. Netw.},
volume = {27},
number = {6},
pages = {2192--2207},
year = {2019},
url = {https://doi.org/10.1109/TNET.2019.2935043},
doi = {10.1109/TNET.2019.2935043},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ton/AvnerM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/EfroniDSM19,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
title = {How to Combine Tree-Search Methods in Reinforcement Learning},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {3494--3501},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33013494},
doi = {10.1609/AAAI.V33I01.33013494},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/EfroniDSM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KozdobaMTM19,
author = {Mark Kozdoba and
Jakub Marecek and
Tigran T. Tchrakian and
Shie Mannor},
title = {On-Line Learning of Linear Dynamical Systems: Exponential Forgetting
in Kalman Filters},
booktitle = {The Thirty-Third {AAAI} Conference on Artificial Intelligence, {AAAI}
2019, The Thirty-First Innovative Applications of Artificial Intelligence
Conference, {IAAI} 2019, The Ninth {AAAI} Symposium on Educational
Advances in Artificial Intelligence, {EAAI} 2019, Honolulu, Hawaii,
USA, January 27 - February 1, 2019},
pages = {4098--4105},
publisher = {{AAAI} Press},
year = {2019},
url = {https://doi.org/10.1609/aaai.v33i01.33014098},
doi = {10.1609/AAAI.V33I01.33014098},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KozdobaMTM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MerlisM19,
author = {Nadav Merlis and
Shie Mannor},
editor = {Alina Beygelzimer and
Daniel Hsu},
title = {Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed
Bandit Problem},
booktitle = {Conference on Learning Theory, {COLT} 2019, 25-28 June 2019, Phoenix,
AZ, {USA}},
series = {Proceedings of Machine Learning Research},
volume = {99},
pages = {2465--2489},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v99/merlis19a.html},
timestamp = {Mon, 08 Jul 2019 16:13:41 +0200},
biburl = {https://dblp.org/rec/conf/colt/MerlisM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/TesslerMM19,
author = {Chen Tessler and
Daniel J. Mankowitz and
Shie Mannor},
title = {Reward Constrained Policy Optimization},
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=SkfrvsA9FX},
timestamp = {Thu, 25 Jul 2019 13:03:15 +0200},
biburl = {https://dblp.org/rec/conf/iclr/TesslerMM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/QuMX19,
author = {Chao Qu and
Shie Mannor and
Huan Xu},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Nonlinear Distributional Gradient Temporal-Difference Learning},
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 = {5251--5260},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/qu19b.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/QuMX19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ShaniEM19,
author = {Lior Shani and
Yonathan Efroni and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Exploration Conscious Reinforcement Learning Revisited},
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 = {5680--5689},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/shani19a.html},
timestamp = {Tue, 11 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ShaniEM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TennenholtzM19,
author = {Guy Tennenholtz and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {The Natural Language of Actions},
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 = {6196--6205},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/tennenholtz19a.html},
timestamp = {Tue, 11 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/TennenholtzM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TesslerEM19,
author = {Chen Tessler and
Yonathan Efroni and
Shie Mannor},
editor = {Kamalika Chaudhuri and
Ruslan Salakhutdinov},
title = {Action Robust Reinforcement Learning and Applications in Continuous
Control},
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 = {6215--6224},
publisher = {{PMLR}},
year = {2019},
url = {http://proceedings.mlr.press/v97/tessler19a.html},
timestamp = {Tue, 11 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/TesslerEM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/QuMXQSX19,
author = {Chao Qu and
Shie Mannor and
Huan Xu and
Yuan Qi and
Le Song and
Junwu Xiong},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement
Learning},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {1182--1191},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/8a0e1141fd37fa5b98d5bb769ba1a7cc-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/QuMXQSX19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TesslerTM19,
author = {Chen Tessler and
Guy Tennenholtz and
Shie Mannor},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Distributional Policy Optimization: An Alternative Approach for Continuous
Control},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {1350--1360},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/72da7fd6d1302c0a159f6436d01e9eb0-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TesslerTM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/EfroniMGM19,
author = {Yonathan Efroni and
Nadav Merlis and
Mohammad Ghavamzadeh and
Shie Mannor},
editor = {Hanna M. Wallach and
Hugo Larochelle and
Alina Beygelzimer and
Florence d'Alch{\'{e}}{-}Buc and
Emily B. Fox and
Roman Garnett},
title = {Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy
Policies},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference
on Neural Information Processing Systems 2019, NeurIPS 2019, December
8-14, 2019, Vancouver, BC, Canada},
pages = {12203--12213},
year = {2019},
url = {https://proceedings.neurips.cc/paper/2019/hash/25caef3a545a1fff2ff4055484f0e758-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/EfroniMGM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/DermanMMM19,
author = {Esther Derman and
Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
editor = {Amir Globerson and
Ricardo Silva},
title = {A Bayesian Approach to Robust Reinforcement Learning},
booktitle = {Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2019, Tel Aviv, Israel, July 22-25, 2019},
series = {Proceedings of Machine Learning Research},
volume = {115},
pages = {648--658},
publisher = {{AUAI} Press},
year = {2019},
url = {http://proceedings.mlr.press/v115/derman20a.html},
timestamp = {Tue, 15 Dec 2020 17:40:18 +0100},
biburl = {https://dblp.org/rec/conf/uai/DermanMMM19.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-07860,
author = {Shirli Di{-}Castro Shashua and
Shie Mannor},
title = {Trust Region Value Optimization using Kalman Filtering},
journal = {CoRR},
volume = {abs/1901.07860},
year = {2019},
url = {http://arxiv.org/abs/1901.07860},
eprinttype = {arXiv},
eprint = {1901.07860},
timestamp = {Sat, 02 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-07860.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-08612,
author = {Tom Zahavy and
Shie Mannor},
title = {Deep Neural Linear Bandits: Overcoming Catastrophic Forgetting through
Likelihood Matching},
journal = {CoRR},
volume = {abs/1901.08612},
year = {2019},
url = {http://arxiv.org/abs/1901.08612},
eprinttype = {arXiv},
eprint = {1901.08612},
timestamp = {Sat, 02 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-08612.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-09184,
author = {Chen Tessler and
Yonathan Efroni and
Shie Mannor},
title = {Action Robust Reinforcement Learning and Applications in Continuous
Control},
journal = {CoRR},
volume = {abs/1901.09184},
year = {2019},
url = {http://arxiv.org/abs/1901.09184},
eprinttype = {arXiv},
eprint = {1901.09184},
timestamp = {Sat, 02 Feb 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-09184.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1901-09326,
author = {Chao Qu and
Shie Mannor and
Huan Xu and
Yuan Qi and
Le Song and
Junwu Xiong},
title = {Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1901.09326},
year = {2019},
url = {http://arxiv.org/abs/1901.09326},
eprinttype = {arXiv},
eprint = {1901.09326},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1901-09326.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-01119,
author = {Guy Tennenholtz and
Shie Mannor},
title = {The Natural Language of Actions},
journal = {CoRR},
volume = {abs/1902.01119},
year = {2019},
url = {http://arxiv.org/abs/1902.01119},
eprinttype = {arXiv},
eprint = {1902.01119},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-01119.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1902-04376,
author = {Xavier Fontaine and
Shie Mannor and
Vianney Perchet},
title = {A Problem-Adaptive Algorithm for Resource Allocation},
journal = {CoRR},
volume = {abs/1902.04376},
year = {2019},
url = {http://arxiv.org/abs/1902.04376},
eprinttype = {arXiv},
eprint = {1902.04376},
timestamp = {Tue, 21 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1902-04376.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-02234,
author = {Shreyansh Gandhi and
Samrat Kokkula and
Abon Chaudhuri and
Alessandro Magnani and
Theban Stanley and
Behzad Ahmadi and
Venkatesh Kandaswamy and
Omer Ovenc and
Shie Mannor},
title = {Image Matters: Detecting Offensive and Non-Compliant Content / Logo
in Product Images},
journal = {CoRR},
volume = {abs/1905.02234},
year = {2019},
url = {http://arxiv.org/abs/1905.02234},
eprinttype = {arXiv},
eprint = {1905.02234},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-02234.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-03125,
author = {Nadav Merlis and
Shie Mannor},
title = {Batch-Size Independent Regret Bounds for the Combinatorial Multi-Armed
Bandit Problem},
journal = {CoRR},
volume = {abs/1905.03125},
year = {2019},
url = {http://arxiv.org/abs/1905.03125},
eprinttype = {arXiv},
eprint = {1905.03125},
timestamp = {Mon, 27 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-03125.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-08188,
author = {Esther Derman and
Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
title = {A Bayesian Approach to Robust Reinforcement Learning},
journal = {CoRR},
volume = {abs/1905.08188},
year = {2019},
url = {http://arxiv.org/abs/1905.08188},
eprinttype = {arXiv},
eprint = {1905.08188},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-08188.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-09700,
author = {Chen Tessler and
Tom Zahavy and
Deborah Cohen and
Daniel J. Mankowitz and
Shie Mannor},
title = {Action Assembly: Sparse Imitation Learning for Text Based Games with
Combinatorial Action Spaces},
journal = {CoRR},
volume = {abs/1905.09700},
year = {2019},
url = {http://arxiv.org/abs/1905.09700},
eprinttype = {arXiv},
eprint = {1905.09700},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-09700.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-09710,
author = {Philip Korsunsky and
Stav Belogolovsky and
Tom Zahavy and
Chen Tessler and
Shie Mannor},
title = {Inverse Reinforcement Learning in Contextual MDPs},
journal = {CoRR},
volume = {abs/1905.09710},
year = {2019},
url = {http://arxiv.org/abs/1905.09710},
eprinttype = {arXiv},
eprint = {1905.09710},
timestamp = {Mon, 03 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-09710.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-09855,
author = {Chen Tessler and
Guy Tennenholtz and
Shie Mannor},
title = {Distributional Policy Optimization: An Alternative Approach for Continuous
Control},
journal = {CoRR},
volume = {abs/1905.09855},
year = {2019},
url = {http://arxiv.org/abs/1905.09855},
eprinttype = {arXiv},
eprint = {1905.09855},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-09855.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1905-11527,
author = {Yonathan Efroni and
Nadav Merlis and
Mohammad Ghavamzadeh and
Shie Mannor},
title = {Tight Regret Bounds for Model-Based Reinforcement Learning with Greedy
Policies},
journal = {CoRR},
volume = {abs/1905.11527},
year = {2019},
url = {http://arxiv.org/abs/1905.11527},
eprinttype = {arXiv},
eprint = {1905.11527},
timestamp = {Mon, 03 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1905-11527.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-05591,
author = {Mark Kozdoba and
Edward Moroshko and
Shie Mannor and
Koby Crammer},
title = {Variance Estimation For Online Regression via Spectrum Thresholding},
journal = {CoRR},
volume = {abs/1906.05591},
year = {2019},
url = {http://arxiv.org/abs/1906.05591},
eprinttype = {arXiv},
eprint = {1906.05591},
timestamp = {Mon, 24 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-05591.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1906-06181,
author = {Dan Fisher and
Mark Kozdoba and
Shie Mannor},
title = {Topic Modeling via Full Dependence Mixtures},
journal = {CoRR},
volume = {abs/1906.06181},
year = {2019},
url = {http://arxiv.org/abs/1906.06181},
eprinttype = {arXiv},
eprint = {1906.06181},
timestamp = {Mon, 24 Jun 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1906-06181.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1908-08379,
author = {Dotan Di Castro and
Joel Oren and
Shie Mannor},
title = {Practical Risk Measures in Reinforcement Learning},
journal = {CoRR},
volume = {abs/1908.08379},
year = {2019},
url = {http://arxiv.org/abs/1908.08379},
eprinttype = {arXiv},
eprint = {1908.08379},
timestamp = {Mon, 26 Aug 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1908-08379.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-02769,
author = {Lior Shani and
Yonathan Efroni and
Shie Mannor},
title = {Adaptive Trust Region Policy Optimization: Global Convergence and
Faster Rates for Regularized MDPs},
journal = {CoRR},
volume = {abs/1909.02769},
year = {2019},
url = {http://arxiv.org/abs/1909.02769},
eprinttype = {arXiv},
eprint = {1909.02769},
timestamp = {Mon, 16 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-02769.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-03739,
author = {Guy Tennenholtz and
Shie Mannor and
Uri Shalit},
title = {Off-Policy Evaluation in Partially Observable Environments},
journal = {CoRR},
volume = {abs/1909.03739},
year = {2019},
url = {http://arxiv.org/abs/1909.03739},
eprinttype = {arXiv},
eprint = {1909.03739},
timestamp = {Tue, 17 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-03739.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-04236,
author = {Yonathan Efroni and
Mohammad Ghavamzadeh and
Shie Mannor},
title = {Multi-Step Greedy and Approximate Real Time Dynamic Programming},
journal = {CoRR},
volume = {abs/1909.04236},
year = {2019},
url = {http://arxiv.org/abs/1909.04236},
eprinttype = {arXiv},
eprint = {1909.04236},
timestamp = {Tue, 17 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1909-04236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-01062,
author = {Chen Tessler and
Nadav Merlis and
Shie Mannor},
title = {Stabilizing Off-Policy Reinforcement Learning with Conservative Policy
Gradients},
journal = {CoRR},
volume = {abs/1910.01062},
year = {2019},
url = {http://arxiv.org/abs/1910.01062},
eprinttype = {arXiv},
eprint = {1910.01062},
timestamp = {Fri, 04 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-01062.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1910-02789,
author = {Erez Schwartz and
Guy Tennenholtz and
Chen Tessler and
Shie Mannor},
title = {Natural Language State Representation for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1910.02789},
year = {2019},
url = {http://arxiv.org/abs/1910.02789},
eprinttype = {arXiv},
eprint = {1910.02789},
timestamp = {Wed, 09 Oct 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-02789.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/KozdobaM18,
author = {Mark Kozdoba and
Shie Mannor},
title = {Source Estimation in Time Series and the Surprising Resilience of
HMMs},
journal = {{IEEE} Trans. Inf. Theory},
volume = {64},
number = {8},
pages = {5555--5569},
year = {2018},
url = {https://doi.org/10.1109/TIT.2018.2832050},
doi = {10.1109/TIT.2018.2832050},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tit/KozdobaM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tnse/MeiromCMOS18,
author = {Eli A. Meirom and
Constantine Caramanis and
Shie Mannor and
Ariel Orda and
Sanjay Shakkottai},
title = {Detecting Cascades from Weak Signatures},
journal = {{IEEE} Trans. Netw. Sci. Eng.},
volume = {5},
number = {4},
pages = {313--325},
year = {2018},
url = {https://doi.org/10.1109/TNSE.2017.2764444},
doi = {10.1109/TNSE.2017.2764444},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tnse/MeiromCMOS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/DalalSTM18,
author = {Gal Dalal and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Gugan Thoppe and
Shie Mannor},
editor = {Sheila A. McIlraith and
Kilian Q. Weinberger},
title = {Finite Sample Analyses for {TD(0)} With Function Approximation},
booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Artificial Intelligence
(IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
2-7, 2018},
pages = {6144--6160},
publisher = {{AAAI} Press},
year = {2018},
url = {https://doi.org/10.1609/aaai.v32i1.12079},
doi = {10.1609/AAAI.V32I1.12079},
timestamp = {Mon, 04 Sep 2023 12:29:24 +0200},
biburl = {https://dblp.org/rec/conf/aaai/DalalSTM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/MankowitzMBPM18,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Pierre{-}Luc Bacon and
Doina Precup and
Shie Mannor},
editor = {Sheila A. McIlraith and
Kilian Q. Weinberger},
title = {Learning Robust Options},
booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Artificial Intelligence
(IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
2-7, 2018},
pages = {6409--6416},
publisher = {{AAAI} Press},
year = {2018},
url = {https://doi.org/10.1609/aaai.v32i1.12115},
doi = {10.1609/AAAI.V32I1.12115},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/MankowitzMBPM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/ZahavyKMM18,
author = {Tom Zahavy and
Abhinandan Krishnan and
Alessandro Magnani and
Shie Mannor},
editor = {Sheila A. McIlraith and
Kilian Q. Weinberger},
title = {Is a Picture Worth a Thousand Words? {A} Deep Multi-Modal Architecture
for Product Classification in E-Commerce},
booktitle = {Proceedings of the Thirty-Second {AAAI} Conference on Artificial Intelligence,
(AAAI-18), the 30th innovative Applications of Artificial Intelligence
(IAAI-18), and the 8th {AAAI} Symposium on Educational Advances in
Artificial Intelligence (EAAI-18), New Orleans, Louisiana, USA, February
2-7, 2018},
pages = {7873--7881},
publisher = {{AAAI} Press},
year = {2018},
url = {https://doi.org/10.1609/aaai.v32i1.11419},
doi = {10.1609/AAAI.V32I1.11419},
timestamp = {Mon, 04 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/ZahavyKMM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/DalalTSM18,
author = {Gal Dalal and
Gugan Thoppe and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Shie Mannor},
editor = {S{\'{e}}bastien Bubeck and
Vianney Perchet and
Philippe Rigollet},
title = {Finite Sample Analysis of Two-Timescale Stochastic Approximation with
Applications to Reinforcement Learning},
booktitle = {Conference On Learning Theory, {COLT} 2018, Stockholm, Sweden, 6-9
July 2018},
series = {Proceedings of Machine Learning Research},
volume = {75},
pages = {1199--1233},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v75/dalal18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:23 +0200},
biburl = {https://dblp.org/rec/conf/colt/DalalTSM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/CasselMZ18,
author = {Asaf B. Cassel and
Shie Mannor and
Assaf Zeevi},
editor = {S{\'{e}}bastien Bubeck and
Vianney Perchet and
Philippe Rigollet},
title = {A General Approach to Multi-Armed Bandits Under Risk Criteria},
booktitle = {Conference On Learning Theory, {COLT} 2018, Stockholm, Sweden, 6-9
July 2018},
series = {Proceedings of Machine Learning Research},
volume = {75},
pages = {1295--1306},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v75/cassel18a.html},
timestamp = {Sun, 03 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/CasselMZ18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/HaroushZMM18,
author = {Matan Haroush and
Tom Zahavy and
Daniel J. Mankowitz and
Shie Mannor},
title = {Learning How Not to Act in Text-based Games},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=B1-tVX1Pz},
timestamp = {Thu, 04 Apr 2019 13:20:09 +0200},
biburl = {https://dblp.org/rec/conf/iclr/HaroushZMM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/ZahavyKSFXM18,
author = {Tom Zahavy and
Bingyi Kang and
Alex Sivak and
Jiashi Feng and
Huan Xu and
Shie Mannor},
title = {Ensemble Robustness and Generalization of Stochastic Deep Learning
Algorithms},
booktitle = {6th International Conference on Learning Representations, {ICLR} 2018,
Vancouver, BC, Canada, April 30 - May 3, 2018, Workshop Track Proceedings},
publisher = {OpenReview.net},
year = {2018},
url = {https://openreview.net/forum?id=HyJf8QJDz},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/iclr/ZahavyKSFXM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/EfroniDSM18,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
editor = {Jennifer G. Dy and
Andreas Krause},
title = {Beyond the One-Step Greedy Approach in Reinforcement Learning},
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 = {1386--1395},
publisher = {{PMLR}},
year = {2018},
url = {http://proceedings.mlr.press/v80/efroni18a.html},
timestamp = {Wed, 03 Apr 2019 18:17:30 +0200},
biburl = {https://dblp.org/rec/conf/icml/EfroniDSM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/DavidSGMS18,
author = {Yahel David and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Mohammad Ghavamzadeh and
Shie Mannor and
Nahum Shimkin},
title = {{PAC} Bandits with Risk Constraints},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2018, Fort Lauderdale, Florida, USA, January 3-5, 2018},
year = {2018},
url = {https://isaim2018.cs.ou.edu/papers/ISAIM2018\_ML\_David\_etal.pdf},
timestamp = {Wed, 20 Mar 2024 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isaim/DavidSGMS18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ZahavyHMMM18,
author = {Tom Zahavy and
Matan Haroush and
Nadav Merlis and
Daniel J. Mankowitz and
Shie Mannor},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Learn What Not to Learn: Action Elimination with Deep Reinforcement
Learning},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {3566--3577},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/645098b086d2f9e1e0e939c27f9f2d6f-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/ZahavyHMMM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/EfroniDSM18,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
editor = {Samy Bengio and
Hanna M. Wallach and
Hugo Larochelle and
Kristen Grauman and
Nicol{\`{o}} Cesa{-}Bianchi and
Roman Garnett},
title = {Multiple-Step Greedy Policies in Approximate and Online Reinforcement
Learning},
booktitle = {Advances in Neural Information Processing Systems 31: Annual Conference
on Neural Information Processing Systems 2018, NeurIPS 2018, December
3-8, 2018, Montr{\'{e}}al, Canada},
pages = {5244--5253},
year = {2018},
url = {https://proceedings.neurips.cc/paper/2018/hash/3f998e713a6e02287c374fd26835d87e-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/EfroniDSM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/uai/DermanMMM18,
author = {Esther Derman and
Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
editor = {Amir Globerson and
Ricardo Silva},
title = {Soft-Robust Actor-Critic Policy-Gradient},
booktitle = {Proceedings of the Thirty-Fourth Conference on Uncertainty in Artificial
Intelligence, {UAI} 2018, Monterey, California, USA, August 6-10,
2018},
pages = {208--218},
publisher = {{AUAI} Press},
year = {2018},
url = {http://auai.org/uai2018/proceedings/papers/70.pdf},
timestamp = {Wed, 09 Mar 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/uai/DermanMMM18.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1801-00500,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor and
Louis Wehenkel},
title = {Chance-Constrained Outage Scheduling using a Machine Learning Proxy},
journal = {CoRR},
volume = {abs/1801.00500},
year = {2018},
url = {http://arxiv.org/abs/1801.00500},
eprinttype = {arXiv},
eprint = {1801.00500},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1801-00500.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-03236,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Pierre{-}Luc Bacon and
Doina Precup and
Shie Mannor},
title = {Learning Robust Options},
journal = {CoRR},
volume = {abs/1802.03236},
year = {2018},
url = {http://arxiv.org/abs/1802.03236},
eprinttype = {arXiv},
eprint = {1802.03236},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-03236.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-03654,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
title = {Beyond the One Step Greedy Approach in Reinforcement Learning},
journal = {CoRR},
volume = {abs/1802.03654},
year = {2018},
url = {http://arxiv.org/abs/1802.03654},
eprinttype = {arXiv},
eprint = {1802.03654},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-03654.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1802-05846,
author = {Guy Tennenholtz and
Tom Zahavy and
Shie Mannor},
title = {Train on Validation: Squeezing the Data Lemon},
journal = {CoRR},
volume = {abs/1802.05846},
year = {2018},
url = {http://arxiv.org/abs/1802.05846},
eprinttype = {arXiv},
eprint = {1802.05846},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1802-05846.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-04848,
author = {Esther Derman and
Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
title = {Soft-Robust Actor-Critic Policy-Gradient},
journal = {CoRR},
volume = {abs/1803.04848},
year = {2018},
url = {http://arxiv.org/abs/1803.04848},
eprinttype = {arXiv},
eprint = {1803.04848},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-04848.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1803-06024,
author = {Tom Zahavy and
Alex Dikopoltsev and
Oren Cohen and
Shie Mannor and
Mordechai Segev},
title = {Deep Learning Reconstruction of Ultra-Short Pulses},
journal = {CoRR},
volume = {abs/1803.06024},
year = {2018},
url = {http://arxiv.org/abs/1803.06024},
eprinttype = {arXiv},
eprint = {1803.06024},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1803-06024.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1804-03958,
author = {Mark Kozdoba and
Shie Mannor},
title = {Interdependent Gibbs Samplers},
journal = {CoRR},
volume = {abs/1804.03958},
year = {2018},
url = {http://arxiv.org/abs/1804.03958},
eprinttype = {arXiv},
eprint = {1804.03958},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1804-03958.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-07732,
author = {Chao Qu and
Shie Mannor and
Huan Xu},
title = {Nonlinear Distributional Gradient Temporal-Difference Learning},
journal = {CoRR},
volume = {abs/1805.07732},
year = {2018},
url = {http://arxiv.org/abs/1805.07732},
eprinttype = {arXiv},
eprint = {1805.07732},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-07732.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-07956,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
title = {Multiple-Step Greedy Policies in Online and Approximate Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1805.07956},
year = {2018},
url = {http://arxiv.org/abs/1805.07956},
eprinttype = {arXiv},
eprint = {1805.07956},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-07956.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1805-11074,
author = {Chen Tessler and
Daniel J. Mankowitz and
Shie Mannor},
title = {Reward Constrained Policy Optimization},
journal = {CoRR},
volume = {abs/1805.11074},
year = {2018},
url = {http://arxiv.org/abs/1805.11074},
eprinttype = {arXiv},
eprint = {1805.11074},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1805-11074.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1806-01380,
author = {Asaf B. Cassel and
Shie Mannor and
Assaf Zeevi},
title = {A General Approach to Multi-Armed Bandits Under Risk Criteria},
journal = {CoRR},
volume = {abs/1806.01380},
year = {2018},
url = {http://arxiv.org/abs/1806.01380},
eprinttype = {arXiv},
eprint = {1806.01380},
timestamp = {Sun, 03 Jul 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1806-01380.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1808-04875,
author = {Orly Avner and
Shie Mannor},
title = {Multi-user Communication Networks: {A} Coordinated Multi-armed Bandit
Approach},
journal = {CoRR},
volume = {abs/1808.04875},
year = {2018},
url = {http://arxiv.org/abs/1808.04875},
eprinttype = {arXiv},
eprint = {1808.04875},
timestamp = {Sun, 02 Sep 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1808-04875.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-01843,
author = {Yonathan Efroni and
Gal Dalal and
Bruno Scherrer and
Shie Mannor},
title = {How to Combine Tree-Search Methods in Reinforcement Learning},
journal = {CoRR},
volume = {abs/1809.01843},
year = {2018},
url = {http://arxiv.org/abs/1809.01843},
eprinttype = {arXiv},
eprint = {1809.01843},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-01843.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-02121,
author = {Tom Zahavy and
Matan Haroush and
Nadav Merlis and
Daniel J. Mankowitz and
Shie Mannor},
title = {Learn What Not to Learn: Action Elimination with Deep Reinforcement
Learning},
journal = {CoRR},
volume = {abs/1809.02121},
year = {2018},
url = {http://arxiv.org/abs/1809.02121},
eprinttype = {arXiv},
eprint = {1809.02121},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-02121.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-05870,
author = {Mark Kozdoba and
Jakub Marecek and
Tigran T. Tchrakian and
Shie Mannor},
title = {On-Line Learning of Linear Dynamical Systems: Exponential Forgetting
in Kalman Filters},
journal = {CoRR},
volume = {abs/1809.05870},
year = {2018},
url = {http://arxiv.org/abs/1809.05870},
eprinttype = {arXiv},
eprint = {1809.05870},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-05870.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1809-05872,
author = {Nir Baram and
Shie Mannor},
title = {Inspiration Learning through Preferences},
journal = {CoRR},
volume = {abs/1809.05872},
year = {2018},
url = {http://arxiv.org/abs/1809.05872},
eprinttype = {arXiv},
eprint = {1809.05872},
timestamp = {Fri, 05 Oct 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1809-05872.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-05551,
author = {Lior Shani and
Yonathan Efroni and
Shie Mannor},
title = {Revisiting Exploration-Conscious Reinforcement Learning},
journal = {CoRR},
volume = {abs/1812.05551},
year = {2018},
url = {http://arxiv.org/abs/1812.05551},
eprinttype = {arXiv},
eprint = {1812.05551},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-05551.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1812-07010,
author = {Mark Kozdoba and
Edward Moroshko and
Lior Shani and
Takuya Takagi and
Takashi Katoh and
Shie Mannor and
Koby Crammer},
title = {Multi Instance Learning For Unbalanced Data},
journal = {CoRR},
volume = {abs/1812.07010},
year = {2018},
url = {http://arxiv.org/abs/1812.07010},
eprinttype = {arXiv},
eprint = {1812.07010},
timestamp = {Tue, 01 Jan 2019 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1812-07010.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jsac/MeiromMO17,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
title = {Strategic Formation of Heterogeneous Networks},
journal = {{IEEE} J. Sel. Areas Commun.},
volume = {35},
number = {3},
pages = {751--763},
year = {2017},
url = {https://doi.org/10.1109/JSAC.2017.2672339},
doi = {10.1109/JSAC.2017.2672339},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jsac/MeiromMO17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/SegevHMCE17,
author = {Noam Segev and
Maayan Harel and
Shie Mannor and
Koby Crammer and
Ran El{-}Yaniv},
title = {Learn on Source, Refine on Target: {A} Model Transfer Learning Framework
with Random Forests},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {39},
number = {9},
pages = {1811--1824},
year = {2017},
url = {https://doi.org/10.1109/TPAMI.2016.2618118},
doi = {10.1109/TPAMI.2016.2618118},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/SegevHMCE17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/siamcomp/AlonCGMMS17,
author = {Noga Alon and
Nicol{\`{o}} Cesa{-}Bianchi and
Claudio Gentile and
Shie Mannor and
Yishay Mansour and
Ohad Shamir},
title = {Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback},
journal = {{SIAM} J. Comput.},
volume = {46},
number = {6},
pages = {1785--1826},
year = {2017},
url = {https://doi.org/10.1137/140989455},
doi = {10.1137/140989455},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/siamcomp/AlonCGMMS17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/TamarCGM17,
author = {Aviv Tamar and
Yinlam Chow and
Mohammad Ghavamzadeh and
Shie Mannor},
title = {Sequential Decision Making With Coherent Risk},
journal = {{IEEE} Trans. Autom. Control.},
volume = {62},
number = {7},
pages = {3323--3338},
year = {2017},
url = {https://doi.org/10.1109/TAC.2016.2644871},
doi = {10.1109/TAC.2016.2644871},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/TamarCGM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TesslerGZMM17,
author = {Chen Tessler and
Shahar Givony and
Tom Zahavy and
Daniel J. Mankowitz and
Shie Mannor},
editor = {Satinder Singh and
Shaul Markovitch},
title = {A Deep Hierarchical Approach to Lifelong Learning in Minecraft},
booktitle = {Proceedings of the Thirty-First {AAAI} Conference on Artificial Intelligence,
February 4-9, 2017, San Francisco, California, {USA}},
pages = {1553--1561},
publisher = {{AAAI} Press},
year = {2017},
url = {https://doi.org/10.1609/aaai.v31i1.10744},
doi = {10.1609/AAAI.V31I1.10744},
timestamp = {Sat, 21 Oct 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TesslerGZMM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/atal/CohensiusMMMO17,
author = {Gal Cohensius and
Shie Mannor and
Reshef Meir and
Eli A. Meirom and
Ariel Orda},
editor = {Kate Larson and
Michael Winikoff and
Sanmay Das and
Edmund H. Durfee},
title = {Proxy Voting for Better Outcomes},
booktitle = {Proceedings of the 16th Conference on Autonomous Agents and MultiAgent
Systems, {AAMAS} 2017, S{\~{a}}o Paulo, Brazil, May 8-12, 2017},
pages = {858--866},
publisher = {{ACM}},
year = {2017},
url = {http://dl.acm.org/citation.cfm?id=3091247},
timestamp = {Wed, 27 Sep 2017 07:24:00 +0200},
biburl = {https://dblp.org/rec/conf/atal/CohensiusMMMO17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/VainsencherMX17,
author = {Daniel Vainsencher and
Shie Mannor and
Huan Xu},
editor = {Satyen Kale and
Ohad Shamir},
title = {Ignoring Is a Bliss: Learning with Large Noise Through Reweighting-Minimization},
booktitle = {Proceedings of the 30th Conference on Learning Theory, {COLT} 2017,
Amsterdam, The Netherlands, 7-10 July 2017},
series = {Proceedings of Machine Learning Research},
volume = {65},
pages = {1849--1881},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v65/vainsencher17a.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/VainsencherMX17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BaramACM17,
author = {Nir Baram and
Oron Anschel and
Itai Caspi and
Shie Mannor},
editor = {Doina Precup and
Yee Whye Teh},
title = {End-to-End Differentiable Adversarial Imitation Learning},
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 = {390--399},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/baram17a.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/BaramACM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Busa-FeketeSWM17,
author = {R{\'{o}}bert Busa{-}Fekete and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Paul Weng and
Shie Mannor},
editor = {Doina Precup and
Yee Whye Teh},
title = {Multi-objective Bandits: Optimizing the Generalized Gini Index},
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 = {625--634},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/busa-fekete17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/Busa-FeketeSWM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HallakM17,
author = {Assaf Hallak and
Shie Mannor},
editor = {Doina Precup and
Yee Whye Teh},
title = {Consistent On-Line Off-Policy Evaluation},
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 = {1372--1383},
publisher = {{PMLR}},
year = {2017},
url = {http://proceedings.mlr.press/v70/hallak17a.html},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HallakM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/MannMP17,
author = {Timothy A. Mann and
Shie Mannor and
Doina Precup},
editor = {Carles Sierra},
title = {Approximate Value Iteration with Temporally Extended Actions (Extended
Abstract)},
booktitle = {Proceedings of the Twenty-Sixth International Joint Conference on
Artificial Intelligence, {IJCAI} 2017, Melbourne, Australia, August
19-25, 2017},
pages = {5035--5039},
publisher = {ijcai.org},
year = {2017},
url = {https://doi.org/10.24963/ijcai.2017/717},
doi = {10.24963/IJCAI.2017/717},
timestamp = {Tue, 20 Aug 2019 16:16:54 +0200},
biburl = {https://dblp.org/rec/conf/ijcai/MannMP17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isgt/CanyasseDM17,
author = {Rapha{\"{e}}l Canyasse and
Gal Dalal and
Shie Mannor},
title = {Supervised learning for optimal power flow as a real-time proxy},
booktitle = {{IEEE} Power {\&} Energy Society Innovative Smart Grid Technologies
Conference, {ISGT} 2017, Washington, DC, USA, April 23-26, 2017},
pages = {1--5},
publisher = {{IEEE}},
year = {2017},
url = {https://doi.org/10.1109/ISGT.2017.8086083},
doi = {10.1109/ISGT.2017.8086083},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isgt/CanyasseDM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LevineCM17,
author = {Nir Levine and
Koby Crammer and
Shie Mannor},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Rotting Bandits},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {3074--3083},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/97d98119037c5b8a9663cb21fb8ebf47-Abstract.html},
timestamp = {Thu, 21 Jan 2021 13:58:27 +0100},
biburl = {https://dblp.org/rec/conf/nips/LevineCM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LevineZMTM17,
author = {Nir Levine and
Tom Zahavy and
Daniel J. Mankowitz and
Aviv Tamar and
Shie Mannor},
editor = {Isabelle Guyon and
Ulrike von Luxburg and
Samy Bengio and
Hanna M. Wallach and
Rob Fergus and
S. V. N. Vishwanathan and
Roman Garnett},
title = {Shallow Updates for Deep Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 30: Annual Conference
on Neural Information Processing Systems 2017, December 4-9, 2017,
Long Beach, CA, {USA}},
pages = {3135--3145},
year = {2017},
url = {https://proceedings.neurips.cc/paper/2017/hash/393c55aea738548df743a186d15f3bef-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LevineZMTM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/SzorenyiCM17,
author = {Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Snir Cohen and
Shie Mannor},
editor = {Michelangelo Ceci and
Jaakko Hollm{\'{e}}n and
Ljupco Todorovski and
Celine Vens and
Saso Dzeroski},
title = {Non-parametric Online {AUC} Maximization},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2017, Skopje, Macedonia, September 18-22, 2017, Proceedings,
Part {II}},
series = {Lecture Notes in Computer Science},
volume = {10535},
pages = {575--590},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-3-319-71246-8\_35},
doi = {10.1007/978-3-319-71246-8\_35},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/SzorenyiCM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/www/AbhishekM17,
author = {Vineet Abhishek and
Shie Mannor},
editor = {Rick Barrett and
Rick Cummings and
Eugene Agichtein and
Evgeniy Gabrilovich},
title = {A Nonparametric Sequential Test for Online Randomized Experiments},
booktitle = {Proceedings of the 26th International Conference on World Wide Web
Companion, Perth, Australia, April 3-7, 2017},
pages = {610--616},
publisher = {{ACM}},
year = {2017},
url = {https://doi.org/10.1145/3041021.3054196},
doi = {10.1145/3041021.3054196},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/www/AbhishekM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:reference/ml/Mannor17,
author = {Shie Mannor},
editor = {Claude Sammut and
Geoffrey I. Webb},
title = {\emph{k}-Armed Bandit},
booktitle = {Encyclopedia of Machine Learning and Data Mining},
pages = {687--690},
publisher = {Springer},
year = {2017},
url = {https://doi.org/10.1007/978-1-4899-7687-1\_424},
doi = {10.1007/978-1-4899-7687-1\_424},
timestamp = {Wed, 12 Jul 2017 01:00:00 +0200},
biburl = {https://dblp.org/rec/reference/ml/Mannor17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/FengXM17,
author = {Jiashi Feng and
Huan Xu and
Shie Mannor},
title = {Outlier Robust Online Learning},
journal = {CoRR},
volume = {abs/1701.00251},
year = {2017},
url = {http://arxiv.org/abs/1701.00251},
eprinttype = {arXiv},
eprint = {1701.00251},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/FengXM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HallakM17,
author = {Assaf Hallak and
Shie Mannor},
title = {Consistent On-Line Off-Policy Evaluation},
journal = {CoRR},
volume = {abs/1702.07121},
year = {2017},
url = {http://arxiv.org/abs/1702.07121},
eprinttype = {arXiv},
eprint = {1702.07121},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HallakM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LevineCM17,
author = {Nir Levine and
Koby Crammer and
Shie Mannor},
title = {Rotting Bandits},
journal = {CoRR},
volume = {abs/1702.07274},
year = {2017},
url = {http://arxiv.org/abs/1702.07274},
eprinttype = {arXiv},
eprint = {1702.07274},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LevineCM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/CohenM17,
author = {Alon Cohen and
Shie Mannor},
title = {Online Learning with Many Experts},
journal = {CoRR},
volume = {abs/1702.07870},
year = {2017},
url = {http://arxiv.org/abs/1702.07870},
eprinttype = {arXiv},
eprint = {1702.07870},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/CohenM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ShashuaM17,
author = {Shirli Di{-}Castro Shashua and
Shie Mannor},
title = {Deep Robust Kalman Filter},
journal = {CoRR},
volume = {abs/1703.02310},
year = {2017},
url = {http://arxiv.org/abs/1703.02310},
eprinttype = {arXiv},
eprint = {1703.02310},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ShashuaM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalSTM17,
author = {Gal Dalal and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Gugan Thoppe and
Shie Mannor},
title = {Concentration Bounds for Two Timescale Stochastic Approximation with
Applications to Reinforcement Learning},
journal = {CoRR},
volume = {abs/1703.05376},
year = {2017},
url = {http://arxiv.org/abs/1703.05376},
eprinttype = {arXiv},
eprint = {1703.05376},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalSTM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalSTM17a,
author = {Gal Dalal and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Gugan Thoppe and
Shie Mannor},
title = {Finite Sample Analysis for {TD(0)} with Linear Function Approximation},
journal = {CoRR},
volume = {abs/1704.01161},
year = {2017},
url = {http://arxiv.org/abs/1704.01161},
eprinttype = {arXiv},
eprint = {1704.01161},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalSTM17a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LevineZMTM17,
author = {Nir Levine and
Tom Zahavy and
Daniel J. Mankowitz and
Aviv Tamar and
Shie Mannor},
title = {Shallow Updates for Deep Reinforcement Learning},
journal = {CoRR},
volume = {abs/1705.07461},
year = {2017},
url = {http://arxiv.org/abs/1705.07461},
eprinttype = {arXiv},
eprint = {1705.07461},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LevineZMTM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Busa-FeketeSWM17,
author = {R{\'{o}}bert Busa{-}Fekete and
Bal{\'{a}}zs Sz{\"{o}}r{\'{e}}nyi and
Paul Weng and
Shie Mannor},
title = {Multi-objective Bandits: Optimizing the Generalized Gini Index},
journal = {CoRR},
volume = {abs/1706.04933},
year = {2017},
url = {http://arxiv.org/abs/1706.04933},
eprinttype = {arXiv},
eprint = {1706.04933},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Busa-FeketeSWM17.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-07832,
author = {Daniel J. Mankowitz and
Aviv Tamar and
Shie Mannor},
title = {Situationally Aware Options},
journal = {CoRR},
volume = {abs/1711.07832},
year = {2017},
url = {http://arxiv.org/abs/1711.07832},
eprinttype = {arXiv},
eprint = {1711.07832},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-07832.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1711-08237,
author = {Guy Tennenholtz and
Constantine Caramanis and
Shie Mannor},
title = {The Stochastic Firefighter Problem},
journal = {CoRR},
volume = {abs/1711.08237},
year = {2017},
url = {http://arxiv.org/abs/1711.08237},
eprinttype = {arXiv},
eprint = {1711.08237},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1711-08237.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ior/XuCM16,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Statistical Optimization in High Dimensions},
journal = {Oper. Res.},
volume = {64},
number = {4},
pages = {958--979},
year = {2016},
url = {https://doi.org/10.1287/opre.2016.1504},
doi = {10.1287/OPRE.2016.1504},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ior/XuCM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/TamarCM16,
author = {Aviv Tamar and
Dotan Di Castro and
Shie Mannor},
title = {Learning the Variance of the Reward-To-Go},
journal = {J. Mach. Learn. Res.},
volume = {17},
pages = {13:1--13:36},
year = {2016},
url = {http://jmlr.org/papers/v17/14-335.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/TamarCM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/FarahmandGSM16,
author = {Amir{-}massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
title = {Regularized Policy Iteration with Nonparametric Function Spaces},
journal = {J. Mach. Learn. Res.},
volume = {17},
pages = {139:1--139:66},
year = {2016},
url = {http://jmlr.org/papers/v17/13-016.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/FarahmandGSM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/LimXM16,
author = {Shiau Hong Lim and
Huan Xu and
Shie Mannor},
title = {Reinforcement Learning in Robust Markov Decision Processes},
journal = {Math. Oper. Res.},
volume = {41},
number = {4},
pages = {1325--1353},
year = {2016},
url = {https://doi.org/10.1287/moor.2016.0779},
doi = {10.1287/MOOR.2016.0779},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mor/LimXM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/MannorMX16,
author = {Shie Mannor and
Ofir Mebel and
Huan Xu},
title = {Robust MDPs with \emph{k}-Rectangular Uncertainty},
journal = {Math. Oper. Res.},
volume = {41},
number = {4},
pages = {1484--1509},
year = {2016},
url = {https://doi.org/10.1287/moor.2016.0786},
doi = {10.1287/MOOR.2016.0786},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mor/MannorMX16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/HallakTMM16,
author = {Assaf Hallak and
Aviv Tamar and
R{\'{e}}mi Munos and
Shie Mannor},
editor = {Dale Schuurmans and
Michael P. Wellman},
title = {Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis},
booktitle = {Proceedings of the Thirtieth {AAAI} Conference on Artificial Intelligence,
February 12-17, 2016, Phoenix, Arizona, {USA}},
pages = {1631--1637},
publisher = {{AAAI} Press},
year = {2016},
url = {https://doi.org/10.1609/aaai.v30i1.10227},
doi = {10.1609/AAAI.V30I1.10227},
timestamp = {Mon, 04 Sep 2023 15:08:28 +0200},
biburl = {https://dblp.org/rec/conf/aaai/HallakTMM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AnavaM16,
author = {Oren Anava and
Shie Mannor},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Heteroscedastic Sequences: Beyond Gaussianity},
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 = {755--763},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/anava16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/icml/AnavaM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ZahavyBM16,
author = {Tom Zahavy and
Nir Ben{-}Zrihem and
Shie Mannor},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Graying the black box: Understanding DQNs},
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 = {1899--1908},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/zahavy16.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ZahavyBM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DalalGM16,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor},
editor = {Maria{-}Florina Balcan and
Kilian Q. Weinberger},
title = {Hierarchical Decision Making In Electricity Grid Management},
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 = {2197--2206},
publisher = {JMLR.org},
year = {2016},
url = {http://proceedings.mlr.press/v48/dalal16.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DalalGM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/AvnerM16,
author = {Orly Avner and
Shie Mannor},
title = {Multi-user lax communications: {A} multi-armed bandit approach},
booktitle = {35th Annual {IEEE} International Conference on Computer Communications,
{INFOCOM} 2016, San Francisco, CA, USA, April 10-14, 2016},
pages = {1--9},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/INFOCOM.2016.7524557},
doi = {10.1109/INFOCOM.2016.7524557},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/infocom/AvnerM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MankowitzMM16,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
editor = {Daniel D. Lee and
Masashi Sugiyama and
Ulrike von Luxburg and
Isabelle Guyon and
Roman Garnett},
title = {Adaptive Skills Adaptive Partitions {(ASAP)}},
booktitle = {Advances in Neural Information Processing Systems 29: Annual Conference
on Neural Information Processing Systems 2016, December 5-10, 2016,
Barcelona, Spain},
pages = {1588--1596},
year = {2016},
url = {https://proceedings.neurips.cc/paper/2016/hash/98d6f58ab0dafbb86b083a001561bb34-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MankowitzMM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/PanagiotouZKGZB16,
author = {Nikolaos Panagiotou and
Nikolas Zygouras and
Ioannis Katakis and
Dimitrios Gunopulos and
Nikos Zacheilas and
Ioannis Boutsis and
Vana Kalogeraki and
Stephen Lynch and
Brendan O'Brien and
Dermot Kinane and
Jakub Marecek and
Jia Yuan Yu and
Rudi Verago and
Elizabeth Daly and
Nico Piatkowski and
Thomas Liebig and
Christian Bockermann and
Katharina Morik and
Fran{\c{c}}ois Schnitzler and
Matthias Weidlich and
Avigdor Gal and
Shie Mannor and
Hendrik Stange and
Werner Halft and
Gennady L. Andrienko},
editor = {Bettina Berendt and
Bj{\"{o}}rn Bringmann and
{\'{E}}lisa Fromont and
Gemma C. Garriga and
Pauli Miettinen and
Nikolaj Tatti and
Volker Tresp},
title = {{INSIGHT:} Dynamic Traffic Management Using Heterogeneous Urban Data},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2016, Riva del Garda, Italy, September 19-23, 2016,
Proceedings, Part {III}},
series = {Lecture Notes in Computer Science},
volume = {9853},
pages = {22--26},
publisher = {Springer},
year = {2016},
url = {https://doi.org/10.1007/978-3-319-46131-1\_5},
doi = {10.1007/978-3-319-46131-1\_5},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pkdd/PanagiotouZKGZB16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pscc/DalalGM16,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor},
title = {Distributed scenario-based optimization for asset management in a
hierarchical decision making environment},
booktitle = {Power Systems Computation Conference, {PSCC} 2016, Genoa, Italy, June
20-24, 2016},
pages = {1--9},
publisher = {{IEEE}},
year = {2016},
url = {https://doi.org/10.1109/PSCC.2016.7540962},
doi = {10.1109/PSCC.2016.7540962},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pscc/DalalGM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalGM16,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor},
title = {Distributed Scenario-Based Optimization for Asset Management in a
Hierarchical Decision Making Environment},
journal = {CoRR},
volume = {abs/1602.01958},
year = {2016},
url = {http://arxiv.org/abs/1602.01958},
eprinttype = {arXiv},
eprint = {1602.01958},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalGM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/FengZKXM16,
author = {Jiashi Feng and
Tom Zahavy and
Bingyi Kang and
Huan Xu and
Shie Mannor},
title = {Ensemble Robustness of Deep Learning Algorithms},
journal = {CoRR},
volume = {abs/1602.02389},
year = {2016},
url = {http://arxiv.org/abs/1602.02389},
eprinttype = {arXiv},
eprint = {1602.02389},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/FengZKXM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZahavyBM16,
author = {Tom Zahavy and
Nir Ben{-}Zrihem and
Shie Mannor},
title = {Graying the black box: Understanding DQNs},
journal = {CoRR},
volume = {abs/1602.02658},
year = {2016},
url = {http://arxiv.org/abs/1602.02658},
eprinttype = {arXiv},
eprint = {1602.02658},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZahavyBM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MankowitzMM16,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
title = {Iterative Hierarchical Optimization for Misspecified Problems {(IHOMP)}},
journal = {CoRR},
volume = {abs/1602.03348},
year = {2016},
url = {http://arxiv.org/abs/1602.03348},
eprinttype = {arXiv},
eprint = {1602.03348},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MankowitzMM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MankowitzMM16a,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
title = {Adaptive Skills, Adaptive Partitions {(ASAP)}},
journal = {CoRR},
volume = {abs/1602.03351},
year = {2016},
url = {http://arxiv.org/abs/1602.03351},
eprinttype = {arXiv},
eprint = {1602.03351},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MankowitzMM16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalGM16a,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor},
title = {Hierarchical Decision Making In Electricity Grid Management},
journal = {CoRR},
volume = {abs/1603.01840},
year = {2016},
url = {http://arxiv.org/abs/1603.01840},
eprinttype = {arXiv},
eprint = {1603.01840},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalGM16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TesslerGZMM16,
author = {Chen Tessler and
Shahar Givony and
Tom Zahavy and
Daniel J. Mankowitz and
Shie Mannor},
title = {A Deep Hierarchical Approach to Lifelong Learning in Minecraft},
journal = {CoRR},
volume = {abs/1604.07255},
year = {2016},
url = {http://arxiv.org/abs/1604.07255},
eprinttype = {arXiv},
eprint = {1604.07255},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TesslerGZMM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MeiromMO16,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
title = {Strategic Formation of Heterogeneous Networks},
journal = {CoRR},
volume = {abs/1604.08179},
year = {2016},
url = {http://arxiv.org/abs/1604.08179},
eprinttype = {arXiv},
eprint = {1604.08179},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MeiromMO16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KozdobaM16,
author = {Mark Kozdoba and
Shie Mannor},
title = {Clustering Time Series and the Surprising Robustness of HMMs},
journal = {CoRR},
volume = {abs/1605.02531},
year = {2016},
url = {http://arxiv.org/abs/1605.02531},
eprinttype = {arXiv},
eprint = {1605.02531},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KozdobaM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HochbergFKMTY16,
author = {Irit Hochberg and
Guy Feraru and
Mark Kozdoba and
Shie Mannor and
Moshe Tennenholtz and
Elad Yom{-}Tov},
title = {A Reinforcement Learning System to Encourage Physical Activity in
Diabetes Patients},
journal = {CoRR},
volume = {abs/1605.04070},
year = {2016},
url = {http://arxiv.org/abs/1605.04070},
eprinttype = {arXiv},
eprint = {1605.04070},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HochbergFKMTY16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RichmanM16,
author = {Oran Richman and
Shie Mannor},
title = {Bending the Curve: Improving the {ROC} Curve Through Error Redistribution},
journal = {CoRR},
volume = {abs/1605.06652},
year = {2016},
url = {http://arxiv.org/abs/1605.06652},
eprinttype = {arXiv},
eprint = {1605.06652},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RichmanM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BaramZM16,
author = {Nir Baram and
Tom Zahavy and
Shie Mannor},
title = {Deep Reinforcement Learning Discovers Internal Models},
journal = {CoRR},
volume = {abs/1606.05174},
year = {2016},
url = {http://arxiv.org/abs/1606.05174},
eprinttype = {arXiv},
eprint = {1606.05174},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/BaramZM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZrihemZM16,
author = {Nir Ben{-}Zrihem and
Tom Zahavy and
Shie Mannor},
title = {Visualizing Dynamics: from t-SNE to SEMI-MDPs},
journal = {CoRR},
volume = {abs/1606.07112},
year = {2016},
url = {http://arxiv.org/abs/1606.07112},
eprinttype = {arXiv},
eprint = {1606.07112},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZrihemZM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/RichmanM16a,
author = {Oran Richman and
Shie Mannor},
title = {How to Allocate Resources For Features Acquisition?},
journal = {CoRR},
volume = {abs/1607.02763},
year = {2016},
url = {http://arxiv.org/abs/1607.02763},
eprinttype = {arXiv},
eprint = {1607.02763},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/RichmanM16a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GhavamzadehMPT16,
author = {Mohammad Ghavamzadeh and
Shie Mannor and
Joelle Pineau and
Aviv Tamar},
title = {Bayesian Reinforcement Learning: {A} Survey},
journal = {CoRR},
volume = {abs/1609.04436},
year = {2016},
url = {http://arxiv.org/abs/1609.04436},
eprinttype = {arXiv},
eprint = {1609.04436},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GhavamzadehMPT16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MankowitzTM16,
author = {Daniel J. Mankowitz and
Aviv Tamar and
Shie Mannor},
title = {Situational Awareness by Risk-Conscious Skills},
journal = {CoRR},
volume = {abs/1610.02847},
year = {2016},
url = {http://arxiv.org/abs/1610.02847},
eprinttype = {arXiv},
eprint = {1610.02847},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MankowitzTM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/CohensiusMMMO16,
author = {Gal Cohensius and
Shie Mannor and
Reshef Meir and
Eli A. Meirom and
Ariel Orda},
title = {Proxy Voting for Better Outcomes},
journal = {CoRR},
volume = {abs/1611.08308},
year = {2016},
url = {http://arxiv.org/abs/1611.08308},
eprinttype = {arXiv},
eprint = {1611.08308},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/CohensiusMMMO16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ZahavyMKM16,
author = {Tom Zahavy and
Alessandro Magnani and
Abhinandan Krishnan and
Shie Mannor},
title = {Is a picture worth a thousand words? {A} Deep Multi-Modal Fusion Architecture
for Product Classification in e-commerce},
journal = {CoRR},
volume = {abs/1611.09534},
year = {2016},
url = {http://arxiv.org/abs/1611.09534},
eprinttype = {arXiv},
eprint = {1611.09534},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/ZahavyMKM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalGMW16,
author = {Gal Dalal and
Elad Gilboa and
Shie Mannor and
Louis Wehenkel},
title = {Unit Commitment using Nearest Neighbor as a Short-Term Proxy},
journal = {CoRR},
volume = {abs/1611.10215},
year = {2016},
url = {http://arxiv.org/abs/1611.10215},
eprinttype = {arXiv},
eprint = {1611.10215},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalGMW16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/BaramAM16,
author = {Nir Baram and
Oron Anschel and
Shie Mannor},
title = {Model-based Adversarial Imitation Learning},
journal = {CoRR},
volume = {abs/1612.02179},
year = {2016},
url = {http://arxiv.org/abs/1612.02179},
eprinttype = {arXiv},
eprint = {1612.02179},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/BaramAM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/CanyasseDM16,
author = {Rapha{\"{e}}l Canyasse and
Gal Dalal and
Shie Mannor},
title = {Supervised Learning for Optimal Power Flow as a Real-Time Proxy},
journal = {CoRR},
volume = {abs/1612.06623},
year = {2016},
url = {http://arxiv.org/abs/1612.06623},
eprinttype = {arXiv},
eprint = {1612.06623},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/CanyasseDM16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MannPMH16,
author = {Timothy A. Mann and
Hugo Penedones and
Shie Mannor and
Todd Hester},
title = {Adaptive Lambda Least-Squares Temporal Difference Learning},
journal = {CoRR},
volume = {abs/1612.09465},
year = {2016},
url = {http://arxiv.org/abs/1612.09465},
eprinttype = {arXiv},
eprint = {1612.09465},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MannPMH16.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ftml/GhavamzadehMPT15,
author = {Mohammad Ghavamzadeh and
Shie Mannor and
Joelle Pineau and
Aviv Tamar},
title = {Bayesian Reinforcement Learning: {A} Survey},
journal = {Found. Trends Mach. Learn.},
volume = {8},
number = {5-6},
pages = {359--483},
year = {2015},
url = {https://doi.org/10.1561/2200000049},
doi = {10.1561/2200000049},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ftml/GhavamzadehMPT15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ior/Ben-TalHKM15,
author = {Aharon Ben{-}Tal and
Elad Hazan and
Tomer Koren and
Shie Mannor},
title = {Oracle-Based Robust Optimization via Online Learning},
journal = {Oper. Res.},
volume = {63},
number = {3},
pages = {628--638},
year = {2015},
url = {https://doi.org/10.1287/opre.2015.1374},
doi = {10.1287/OPRE.2015.1374},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ior/Ben-TalHKM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jair/MannMP15,
author = {Timothy A. Mann and
Shie Mannor and
Doina Precup},
title = {Approximate Value Iteration with Temporally Extended Actions},
journal = {J. Artif. Intell. Res.},
volume = {53},
pages = {375--438},
year = {2015},
url = {https://doi.org/10.1613/jair.4676},
doi = {10.1613/JAIR.4676},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jair/MannMP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/HarelM15,
author = {Maayan Harel and
Shie Mannor},
title = {The Perturbed Variation},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {37},
number = {10},
pages = {2119--2130},
year = {2015},
url = {https://doi.org/10.1109/TPAMI.2015.2404836},
doi = {10.1109/TPAMI.2015.2404836},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/HarelM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/MillingCMS15,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
title = {Distinguishing Infections on Different Graph Topologies},
journal = {{IEEE} Trans. Inf. Theory},
volume = {61},
number = {6},
pages = {3100--3120},
year = {2015},
url = {https://doi.org/10.1109/TIT.2015.2424875},
doi = {10.1109/TIT.2015.2424875},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tit/MillingCMS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/MannMM15,
author = {Timothy A. Mann and
Daniel J. Mankowitz and
Shie Mannor},
editor = {Michael Bowling and
Marc G. Bellemare and
Erik Talvitie and
Joel Veness and
Marlos C. Machado},
title = {Learning When to Switch between Skills in a High Dimensional Domain},
booktitle = {Learning for General Competency in Video Games, Papers from the 2015
{AAAI} Workshop, Austin, Texas, USA, January 26, 2015},
series = {{AAAI} Technical Report},
volume = {{WS-15-10}},
publisher = {{AAAI} Press},
year = {2015},
url = {http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10089},
timestamp = {Tue, 05 Sep 2023 08:59:27 +0200},
biburl = {https://dblp.org/rec/conf/aaai/MannMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/TamarGM15,
author = {Aviv Tamar and
Yonatan Glassner and
Shie Mannor},
editor = {Blai Bonet and
Sven Koenig},
title = {Optimizing the CVaR via Sampling},
booktitle = {Proceedings of the Twenty-Ninth {AAAI} Conference on Artificial Intelligence,
January 25-30, 2015, Austin, Texas, {USA}},
pages = {2993--2999},
publisher = {{AAAI} Press},
year = {2015},
url = {https://doi.org/10.1609/aaai.v29i1.9561},
doi = {10.1609/AAAI.V29I1.9561},
timestamp = {Mon, 18 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/TamarGM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aistats/SchnitzlerYM15,
author = {Fran{\c{c}}ois Schnitzler and
Jia Yuan Yu and
Shie Mannor},
editor = {Guy Lebanon and
S. V. N. Vishwanathan},
title = {Sensor Selection for Crowdsensing Dynamical Systems},
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/schnitzler15.html},
timestamp = {Wed, 29 May 2019 08:41:44 +0200},
biburl = {https://dblp.org/rec/conf/aistats/SchnitzlerYM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/GopalanM15,
author = {Aditya Gopalan and
Shie Mannor},
editor = {Peter Gr{\"{u}}nwald and
Elad Hazan and
Satyen Kale},
title = {Thompson Sampling for Learning Parameterized Markov Decision Processes},
booktitle = {Proceedings of The 28th Conference on Learning Theory, {COLT} 2015,
Paris, France, July 3-6, 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {40},
pages = {861--898},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v40/Gopalan15.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/colt/GopalanM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/RichmanM15,
author = {Oran Richman and
Shie Mannor},
editor = {Francis R. Bach and
David M. Blei},
title = {Dynamic Sensing: Better Classification under Acquisition Constraints},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {267--275},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/richman15.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/RichmanM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HallakSMM15,
author = {Assaf Hallak and
Fran{\c{c}}ois Schnitzler and
Timothy A. Mann and
Shie Mannor},
editor = {Francis R. Bach and
David M. Blei},
title = {Off-policy Model-based Learning under Unknown Factored Dynamics},
booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
{ICML} 2015, Lille, France, 6-11 July 2015},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {37},
pages = {711--719},
publisher = {JMLR.org},
year = {2015},
url = {http://proceedings.mlr.press/v37/hallak15.html},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HallakSMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/MillingCMS15,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
title = {Local detection of infections in heterogeneous networks},
booktitle = {2015 {IEEE} Conference on Computer Communications, {INFOCOM} 2015,
Kowloon, Hong Kong, April 26 - May 1, 2015},
pages = {1517--1525},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/INFOCOM.2015.7218530},
doi = {10.1109/INFOCOM.2015.7218530},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/infocom/MillingCMS15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/MeiromMO15,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
title = {Formation games of reliable networks},
booktitle = {2015 {IEEE} Conference on Computer Communications, {INFOCOM} 2015,
Kowloon, Hong Kong, April 26 - May 1, 2015},
pages = {1760--1768},
publisher = {{IEEE}},
year = {2015},
url = {https://doi.org/10.1109/INFOCOM.2015.7218557},
doi = {10.1109/INFOCOM.2015.7218557},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/infocom/MeiromMO15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isca/PeledMWE15,
author = {Leeor Peled and
Shie Mannor and
Uri C. Weiser and
Yoav Etsion},
editor = {Deborah T. Marr and
David H. Albonesi},
title = {Semantic locality and context-based prefetching using reinforcement
learning},
booktitle = {Proceedings of the 42nd Annual International Symposium on Computer
Architecture, Portland, OR, USA, June 13-17, 2015},
pages = {285--297},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2749469.2749473},
doi = {10.1145/2749469.2749473},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/isca/PeledMWE15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/AnavaHM15,
author = {Oren Anava and
Elad Hazan and
Shie Mannor},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Online Learning for Adversaries with Memory: Price of Past Mistakes},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {784--792},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/38913e1d6a7b94cb0f55994f679f5956-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/AnavaHM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/TamarCGM15,
author = {Aviv Tamar and
Yinlam Chow and
Mohammad Ghavamzadeh and
Shie Mannor},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Policy Gradient for Coherent Risk Measures},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {1468--1476},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/024d7f84fff11dd7e8d9c510137a2381-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/TamarCGM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/ChowTMP15,
author = {Yinlam Chow and
Aviv Tamar and
Shie Mannor and
Marco Pavone},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {1522--1530},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/64223ccf70bbb65a3a4aceac37e21016-Abstract.html},
timestamp = {Mon, 19 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/ChowTMP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/KozdobaM15,
author = {Mark Kozdoba and
Shie Mannor},
editor = {Corinna Cortes and
Neil D. Lawrence and
Daniel D. Lee and
Masashi Sugiyama and
Roman Garnett},
title = {Community Detection via Measure Space Embedding},
booktitle = {Advances in Neural Information Processing Systems 28: Annual Conference
on Neural Information Processing Systems 2015, December 7-12, 2015,
Montreal, Quebec, Canada},
pages = {2890--2898},
year = {2015},
url = {https://proceedings.neurips.cc/paper/2015/hash/973a5f0ccbc4ee3524ccf035d35b284b-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/KozdobaM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmetrics/MeiromMCMSO15,
author = {Eli A. Meirom and
Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai and
Ariel Orda},
editor = {Bill Lin and
Jun (Jim) Xu and
Sudipta Sengupta and
Devavrat Shah},
title = {Localized Epidemic Detection in Networks with Overwhelming Noise},
booktitle = {Proceedings of the 2015 {ACM} {SIGMETRICS} International Conference
on Measurement and Modeling of Computer Systems, Portland, OR, USA,
June 15-19, 2015},
pages = {441--442},
publisher = {{ACM}},
year = {2015},
url = {https://doi.org/10.1145/2745844.2745883},
doi = {10.1145/2745844.2745883},
timestamp = {Mon, 01 Aug 2022 08:51:52 +0200},
biburl = {https://dblp.org/rec/conf/sigmetrics/MeiromMCMSO15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/icml/2015mud,
editor = {Ioannis Katakis and
Fran{\c{c}}ois Schnitzler and
Thomas Liebig and
Dimitrios Gunopulos and
Katharina Morik and
Gennady L. Andrienko and
Shie Mannor},
title = {Proceedings of the 2nd International Workshop on Mining Urban Data
co-located with 32nd International Conference on Machine Learning
{(ICML} 2015), Lille, France, July 11th, 2015},
series = {{CEUR} Workshop Proceedings},
volume = {1392},
publisher = {CEUR-WS.org},
year = {2015},
url = {https://ceur-ws.org/Vol-1392},
urn = {urn:nbn:de:0074-1392-2},
timestamp = {Fri, 10 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/2015mud.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HallakCM15,
author = {Assaf Hallak and
Dotan Di Castro and
Shie Mannor},
title = {Contextual Markov Decision Processes},
journal = {CoRR},
volume = {abs/1502.02259},
year = {2015},
url = {http://arxiv.org/abs/1502.02259},
eprinttype = {arXiv},
eprint = {1502.02259},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HallakCM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HallakSMM15,
author = {Assaf Hallak and
Fran{\c{c}}ois Schnitzler and
Timothy A. Mann and
Shie Mannor},
title = {Off-policy evaluation for MDPs with unknown structure},
journal = {CoRR},
volume = {abs/1502.03255},
year = {2015},
url = {http://arxiv.org/abs/1502.03255},
eprinttype = {arXiv},
eprint = {1502.03255},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HallakSMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TamarCGM15,
author = {Aviv Tamar and
Yinlam Chow and
Mohammad Ghavamzadeh and
Shie Mannor},
title = {Policy Gradient for Coherent Risk Measures},
journal = {CoRR},
volume = {abs/1502.03919},
year = {2015},
url = {http://arxiv.org/abs/1502.03919},
eprinttype = {arXiv},
eprint = {1502.03919},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TamarCGM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/LevineMM15,
author = {Nir Levine and
Timothy A. Mann and
Shie Mannor},
title = {Actively Learning to Attract Followers on Twitter},
journal = {CoRR},
volume = {abs/1504.04114},
year = {2015},
url = {http://arxiv.org/abs/1504.04114},
eprinttype = {arXiv},
eprint = {1504.04114},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/LevineMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KozdobaM15,
author = {Mark Kozdoba and
Shie Mannor},
title = {Overlapping Communities Detection via Measure Space Embedding},
journal = {CoRR},
volume = {abs/1504.06796},
year = {2015},
url = {http://arxiv.org/abs/1504.06796},
eprinttype = {arXiv},
eprint = {1504.06796},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KozdobaM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/KozdobaM15a,
author = {Mark Kozdoba and
Shie Mannor},
title = {Overlapping Community Detection by Online Cluster Aggregation},
journal = {CoRR},
volume = {abs/1504.06798},
year = {2015},
url = {http://arxiv.org/abs/1504.06798},
eprinttype = {arXiv},
eprint = {1504.06798},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/KozdobaM15a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AvnerM15,
author = {Orly Avner and
Shie Mannor},
title = {Learning to coordinate without communication in multi-user multi-armed
bandit problems},
journal = {CoRR},
volume = {abs/1504.08167},
year = {2015},
url = {http://arxiv.org/abs/1504.08167},
eprinttype = {arXiv},
eprint = {1504.08167},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AvnerM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/ChowTMP15,
author = {Yinlam Chow and
Aviv Tamar and
Shie Mannor and
Marco Pavone},
title = {Risk-Sensitive and Robust Decision-Making: a CVaR Optimization Approach},
journal = {CoRR},
volume = {abs/1506.02188},
year = {2015},
url = {http://arxiv.org/abs/1506.02188},
eprinttype = {arXiv},
eprint = {1506.02188},
timestamp = {Mon, 19 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/ChowTMP15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MankowitzMM15,
author = {Daniel J. Mankowitz and
Timothy A. Mann and
Shie Mannor},
title = {Bootstrapping Skills},
journal = {CoRR},
volume = {abs/1506.03624},
year = {2015},
url = {http://arxiv.org/abs/1506.03624},
eprinttype = {arXiv},
eprint = {1506.03624},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MankowitzMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/DalalM15,
author = {Gal Dalal and
Shie Mannor},
title = {Reinforcement Learning for the Unit Commitment Problem},
journal = {CoRR},
volume = {abs/1507.05268},
year = {2015},
url = {http://arxiv.org/abs/1507.05268},
eprinttype = {arXiv},
eprint = {1507.05268},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/DalalM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HallakTM15,
author = {Assaf Hallak and
Aviv Tamar and
Shie Mannor},
title = {Emphatic {TD} Bellman Operator is a Contraction},
journal = {CoRR},
volume = {abs/1508.03411},
year = {2015},
url = {http://arxiv.org/abs/1508.03411},
eprinttype = {arXiv},
eprint = {1508.03411},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HallakTM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/HallakTMM15,
author = {Assaf Hallak and
Aviv Tamar and
R{\'{e}}mi Munos and
Shie Mannor},
title = {Generalized Emphatic Temporal Difference Learning: Bias-Variance Analysis},
journal = {CoRR},
volume = {abs/1509.05172},
year = {2015},
url = {http://arxiv.org/abs/1509.05172},
eprinttype = {arXiv},
eprint = {1509.05172},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/HallakTMM15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/SegevHMCE15,
author = {Noam Segev and
Maayan Harel and
Shie Mannor and
Koby Crammer and
Ran El{-}Yaniv},
title = {Learn on Source, Refine on Target: {A} Model Transfer Learning Framework
with Random Forests},
journal = {CoRR},
volume = {abs/1511.01258},
year = {2015},
url = {http://arxiv.org/abs/1511.01258},
eprinttype = {arXiv},
eprint = {1511.01258},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/SegevHMCE15.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MannorPS14,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
title = {Set-valued approachability and online learning with partial monitoring},
journal = {J. Mach. Learn. Res.},
volume = {15},
number = {1},
pages = {3247--3295},
year = {2014},
url = {https://dl.acm.org/doi/10.5555/2627435.2697069},
doi = {10.5555/2627435.2697069},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorPS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/BernsteinMS14,
author = {Andrey Bernstein and
Shie Mannor and
Nahum Shimkin},
title = {Opportunistic Approachability and Generalized No-Regret Problems},
journal = {Math. Oper. Res.},
volume = {39},
number = {4},
pages = {1057--1083},
year = {2014},
url = {https://doi.org/10.1287/moor.2014.0643},
doi = {10.1287/MOOR.2014.0643},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/BernsteinMS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/CushonHLMG14,
author = {Kevin Cushon and
Saied Hemati and
Camille Leroux and
Shie Mannor and
Warren J. Gross},
title = {High-Throughput Energy-Efficient {LDPC} Decoders Using Differential
Binary Message Passing},
journal = {{IEEE} Trans. Signal Process.},
volume = {62},
number = {3},
pages = {619--631},
year = {2014},
url = {https://doi.org/10.1109/TSP.2013.2293116},
doi = {10.1109/TSP.2013.2293116},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/CushonHLMG14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/asap/CushonHMG14,
author = {Kevin Cushon and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Energy-efficient gear-shift {LDPC} decoders},
booktitle = {{IEEE} 25th International Conference on Application-Specific Systems,
Architectures and Processors, {ASAP} 2014, Zurich, Switzerland, June
18-20, 2014},
pages = {219--223},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/ASAP.2014.6868665},
doi = {10.1109/ASAP.2014.6868665},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/asap/CushonHMG14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorPS14,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
editor = {Maria{-}Florina Balcan and
Vitaly Feldman and
Csaba Szepesv{\'{a}}ri},
title = {Approachability in unknown games: Online learning meets multi-objective
optimization},
booktitle = {Proceedings of The 27th Conference on Learning Theory, {COLT} 2014,
Barcelona, Spain, June 13-15, 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {35},
pages = {339--355},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v35/mannor14.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorPS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/edbt/SchnitzlerLMM14,
author = {Fran{\c{c}}ois Schnitzler and
Thomas Liebig and
Shie Mannor and
Katharina Morik},
editor = {K. Sel{\c{c}}uk Candan and
Sihem Amer{-}Yahia and
Nicole Schweikardt and
Vassilis Christophides and
Vincent Leroy},
title = {Combining a Gauss-Markov model and Gaussian process for traffic prediction
in Dublin city center},
booktitle = {Proceedings of the Workshops of the {EDBT/ICDT} 2014 Joint Conference
{(EDBT/ICDT} 2014), Athens, Greece, March 28, 2014},
series = {{CEUR} Workshop Proceedings},
volume = {1133},
pages = {373--374},
publisher = {CEUR-WS.org},
year = {2014},
url = {https://ceur-ws.org/Vol-1133/paper-62.pdf},
timestamp = {Fri, 10 Mar 2023 16:23:45 +0100},
biburl = {https://dblp.org/rec/conf/edbt/SchnitzlerLMM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/edbt/ArtikisWSBLPBMKMGMGK14,
author = {Alexander Artikis and
Matthias Weidlich and
Fran{\c{c}}ois Schnitzler and
Ioannis Boutsis and
Thomas Liebig and
Nico Piatkowski and
Christian Bockermann and
Katharina Morik and
Vana Kalogeraki and
Jakub Marecek and
Avigdor Gal and
Shie Mannor and
Dimitrios Gunopulos and
Dermot Kinane},
editor = {Sihem Amer{-}Yahia and
Vassilis Christophides and
Anastasios Kementsietsidis and
Minos N. Garofalakis and
Stratos Idreos and
Vincent Leroy},
title = {Heterogeneous Stream Processing and Crowdsourcing for Urban Traffic
Management},
booktitle = {Proceedings of the 17th International Conference on Extending Database
Technology, {EDBT} 2014, Athens, Greece, March 24-28, 2014},
pages = {712--723},
publisher = {OpenProceedings.org},
year = {2014},
url = {https://doi.org/10.5441/002/edbt.2014.77},
doi = {10.5441/002/EDBT.2014.77},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/edbt/ArtikisWSBLPBMKMGMGK14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/GopalanMM14,
author = {Aditya Gopalan and
Shie Mannor and
Yishay Mansour},
title = {Thompson Sampling for Complex Online Problems},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {100--108},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/gopalan14.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/GopalanMM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannM14,
author = {Timothy A. Mann and
Shie Mannor},
title = {Scaling Up Approximate Value Iteration with Options: Better Policies
with Fewer Iterations},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {127--135},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/mann14.html},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MannM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MaillardM14,
author = {Odalric{-}Ambrym Maillard and
Shie Mannor},
title = {Latent Bandits},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {136--144},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/maillard14.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MaillardM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TamarMX14,
author = {Aviv Tamar and
Shie Mannor and
Huan Xu},
title = {Scaling Up Robust MDPs using Function Approximation},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {181--189},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/tamar14.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/TamarMX14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HarelMEC14,
author = {Maayan Harel and
Shie Mannor and
Ran El{-}Yaniv and
Koby Crammer},
title = {Concept Drift Detection Through Resampling},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1009--1017},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/harel14.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HarelMEC14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannMM14,
author = {Timothy A. Mann and
Daniel J. Mankowitz and
Shie Mannor},
title = {Time-Regularized Interrupting Options {(TRIO)}},
booktitle = {Proceedings of the 31th International Conference on Machine Learning,
{ICML} 2014, Beijing, China, 21-26 June 2014},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {32},
pages = {1350--1358},
publisher = {JMLR.org},
year = {2014},
url = {http://proceedings.mlr.press/v32/mannb14.html},
timestamp = {Wed, 17 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MannMM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/micro/FuchsMWE14,
author = {Adi Fuchs and
Shie Mannor and
Uri C. Weiser and
Yoav Etsion},
title = {Loop-Aware Memory Prefetching Using Code Block Working Sets},
booktitle = {47th Annual {IEEE/ACM} International Symposium on Microarchitecture,
{MICRO} 2014, Cambridge, United Kingdom, December 13-17, 2014},
pages = {533--544},
publisher = {{IEEE} Computer Society},
year = {2014},
url = {https://doi.org/10.1109/MICRO.2014.27},
doi = {10.1109/MICRO.2014.27},
timestamp = {Tue, 31 May 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/micro/FuchsMWE14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FengXMY14,
author = {Jiashi Feng and
Huan Xu and
Shie Mannor and
Shuicheng Yan},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {Robust Logistic Regression and Classification},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {253--261},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/6cdd60ea0045eb7a6ec44c54d29ed402-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/FengXMY14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MaillardMM14,
author = {Odalric{-}Ambrym Maillard and
Timothy A. Mann and
Shie Mannor},
editor = {Zoubin Ghahramani and
Max Welling and
Corinna Cortes and
Neil D. Lawrence and
Kilian Q. Weinberger},
title = {How hard is my MDP?" The distribution-norm to the rescue"},
booktitle = {Advances in Neural Information Processing Systems 27: Annual Conference
on Neural Information Processing Systems 2014, December 8-13 2014,
Montreal, Quebec, Canada},
pages = {1835--1843},
year = {2014},
url = {https://proceedings.neurips.cc/paper/2014/hash/2ab56412b1163ee131e1246da0955bd1-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/MaillardMM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/AvnerM14,
author = {Orly Avner and
Shie Mannor},
editor = {Toon Calders and
Floriana Esposito and
Eyke H{\"{u}}llermeier and
Rosa Meo},
title = {Concurrent Bandits and Cognitive Radio Networks},
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 = {66--81},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-662-44848-9\_5},
doi = {10.1007/978-3-662-44848-9\_5},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/AvnerM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/BaransiMM14,
author = {Akram Baransi and
Odalric{-}Ambrym Maillard and
Shie Mannor},
editor = {Toon Calders and
Floriana Esposito and
Eyke H{\"{u}}llermeier and
Rosa Meo},
title = {Sub-sampling for Multi-armed Bandits},
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 = {115--131},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-662-44848-9\_8},
doi = {10.1007/978-3-662-44848-9\_8},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/BaransiMM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/SchnitzlerAWBLPBMKMGMKG14,
author = {Fran{\c{c}}ois Schnitzler and
Alexander Artikis and
Matthias Weidlich and
Ioannis Boutsis and
Thomas Liebig and
Nico Piatkowski and
Christian Bockermann and
Katharina Morik and
Vana Kalogeraki and
Jakub Marecek and
Avigdor Gal and
Shie Mannor and
Dermot Kinane and
Dimitrios Gunopulos},
editor = {Toon Calders and
Floriana Esposito and
Eyke H{\"{u}}llermeier and
Rosa Meo},
title = {Heterogeneous Stream Processing and Crowdsourcing for Traffic Monitoring:
Highlights},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2014, Nancy, France, September 15-19, 2014. Proceedings,
Part {III}},
series = {Lecture Notes in Computer Science},
volume = {8726},
pages = {520--523},
publisher = {Springer},
year = {2014},
url = {https://doi.org/10.1007/978-3-662-44845-8\_49},
doi = {10.1007/978-3-662-44845-8\_49},
timestamp = {Sun, 12 Nov 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/pkdd/SchnitzlerAWBLPBMKMGMKG14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigecom/MeiromMO14,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
editor = {Moshe Babaioff and
Vincent Conitzer and
David A. Easley},
title = {Network formation games with heterogeneous players and the internet
structure},
booktitle = {{ACM} Conference on Economics and Computation, {EC} '14, Stanford
, CA, USA, June 8-12, 2014},
pages = {735--752},
publisher = {{ACM}},
year = {2014},
url = {https://doi.org/10.1145/2600057.2602862},
doi = {10.1145/2600057.2602862},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigecom/MeiromMO14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MeiromMCMOS14,
author = {Eli A. Meirom and
Chris Milling and
Constantine Caramanis and
Shie Mannor and
Ariel Orda and
Sanjay Shakkottai},
title = {Localized epidemic detection in networks with overwhelming noise},
journal = {CoRR},
volume = {abs/1402.1263},
year = {2014},
url = {http://arxiv.org/abs/1402.1263},
eprinttype = {arXiv},
eprint = {1402.1263},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MeiromMCMOS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MannorPS14,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
title = {Approachability in unknown games: Online learning meets multi-objective
optimization},
journal = {CoRR},
volume = {abs/1402.2043},
year = {2014},
url = {http://arxiv.org/abs/1402.2043},
eprinttype = {arXiv},
eprint = {1402.2043},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MannorPS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/Ben-TalHKM14,
author = {Aharon Ben{-}Tal and
Elad Hazan and
Tomer Koren and
Shie Mannor},
title = {Oracle-Based Robust Optimization via Online Learning},
journal = {CoRR},
volume = {abs/1402.6361},
year = {2014},
url = {http://arxiv.org/abs/1402.6361},
eprinttype = {arXiv},
eprint = {1402.6361},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/Ben-TalHKM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TamarGM14,
author = {Aviv Tamar and
Yonatan Glassner and
Shie Mannor},
title = {Policy Gradients Beyond Expectations: Conditional Value-at-Risk},
journal = {CoRR},
volume = {abs/1404.3862},
year = {2014},
url = {http://arxiv.org/abs/1404.3862},
eprinttype = {arXiv},
eprint = {1404.3862},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TamarGM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AvnerM14,
author = {Orly Avner and
Shie Mannor},
title = {Concurrent bandits and cognitive radio networks},
journal = {CoRR},
volume = {abs/1404.5421},
year = {2014},
url = {http://arxiv.org/abs/1404.5421},
eprinttype = {arXiv},
eprint = {1404.5421},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AvnerM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GopalanM14,
author = {Aditya Gopalan and
Shie Mannor},
title = {Thompson Sampling for Learning Parameterized MDPs},
journal = {CoRR},
volume = {abs/1406.7498},
year = {2014},
url = {http://arxiv.org/abs/1406.7498},
eprinttype = {arXiv},
eprint = {1406.7498},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GopalanM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/FengXM14,
author = {Jiashi Feng and
Huan Xu and
Shie Mannor},
title = {Distributed Robust Learning},
journal = {CoRR},
volume = {abs/1409.5937},
year = {2014},
url = {http://arxiv.org/abs/1409.5937},
eprinttype = {arXiv},
eprint = {1409.5937},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/FengXM14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/AlonCGMMS14,
author = {Noga Alon and
Nicol{\`{o}} Cesa{-}Bianchi and
Claudio Gentile and
Shie Mannor and
Yishay Mansour and
Ohad Shamir},
title = {Nonstochastic Multi-Armed Bandits with Graph-Structured Feedback},
journal = {CoRR},
volume = {abs/1409.8428},
year = {2014},
url = {http://arxiv.org/abs/1409.8428},
eprinttype = {arXiv},
eprint = {1409.8428},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/AlonCGMMS14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TamarTMA14,
author = {Aviv Tamar and
Panos Toulis and
Shie Mannor and
Edoardo M. Airoldi},
title = {Implicit Temporal Differences},
journal = {CoRR},
volume = {abs/1412.6734},
year = {2014},
url = {http://arxiv.org/abs/1412.6734},
eprinttype = {arXiv},
eprint = {1412.6734},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TamarTMA14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MeiromMO14,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
title = {Formation Games of Reliable Networks},
journal = {CoRR},
volume = {abs/1412.8501},
year = {2014},
url = {http://arxiv.org/abs/1412.8501},
eprinttype = {arXiv},
eprint = {1412.8501},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MeiromMO14.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/eor/MannorT13,
author = {Shie Mannor and
John N. Tsitsiklis},
title = {Algorithmic aspects of mean-variance optimization in Markov decision
processes},
journal = {Eur. J. Oper. Res.},
volume = {231},
number = {3},
pages = {645--653},
year = {2013},
url = {https://doi.org/10.1016/j.ejor.2013.06.019},
doi = {10.1016/J.EJOR.2013.06.019},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/eor/MannorT13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/geb/ArcauteDJM13,
author = {Esteban Arcaute and
Kirill Dyagilev and
Ramesh Johari and
Shie Mannor},
title = {Dynamics in tree formation games},
journal = {Games Econ. Behav.},
volume = {79},
pages = {1--29},
year = {2013},
url = {https://doi.org/10.1016/j.geb.2013.01.002},
doi = {10.1016/J.GEB.2013.01.002},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/geb/ArcauteDJM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/im/JagannathanMMM13,
author = {Krishna P. Jagannathan and
Shie Mannor and
Ishai Menache and
Eytan H. Modiano},
title = {A State Action Frequency Approach to Throughput Maximization over
Uncertain Wireless Channels},
journal = {Internet Math.},
volume = {9},
number = {2-3},
pages = {136--160},
year = {2013},
url = {https://doi.org/10.1080/15427951.2011.601934},
doi = {10.1080/15427951.2011.601934},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/im/JagannathanMMM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/FrankMPP13,
author = {Jordan Frank and
Shie Mannor and
Joelle Pineau and
Doina Precup},
title = {Time Series Analysis Using Geometric Template Matching},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {35},
number = {3},
pages = {740--754},
year = {2013},
url = {https://doi.org/10.1109/TPAMI.2012.121},
doi = {10.1109/TPAMI.2012.121},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/pami/FrankMPP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/percom/FrankMP13,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
title = {Generating storylines from sensor data},
journal = {Pervasive Mob. Comput.},
volume = {9},
number = {6},
pages = {838--847},
year = {2013},
url = {https://doi.org/10.1016/j.pmcj.2013.07.005},
doi = {10.1016/J.PMCJ.2013.07.005},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/percom/FrankMP13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/snam/DyagilevMY13,
author = {Kirill Dyagilev and
Shie Mannor and
Elad Yom{-}Tov},
title = {On information propagation in mobile call networks},
journal = {Soc. Netw. Anal. Min.},
volume = {3},
number = {3},
pages = {521--541},
year = {2013},
url = {https://doi.org/10.1007/s13278-013-0100-5},
doi = {10.1007/S13278-013-0100-5},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/snam/DyagilevMY13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcom/SarkisHMG13,
author = {Gabi Sarkis and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Stochastic Decoding of {LDPC} Codes over GF(q)},
journal = {{IEEE} Trans. Commun.},
volume = {61},
number = {3},
pages = {939--950},
year = {2013},
url = {https://doi.org/10.1109/TCOMM.2013.012913.110340},
doi = {10.1109/TCOMM.2013.012913.110340},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcom/SarkisHMG13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcom/Leduc-PrimeauHMG13,
author = {Fran{\c{c}}ois Leduc{-}Primeau and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Relaxed Half-Stochastic Belief Propagation},
journal = {{IEEE} Trans. Commun.},
volume = {61},
number = {5},
pages = {1648--1659},
year = {2013},
url = {https://doi.org/10.1109/TCOMM.2013.021913.120149},
doi = {10.1109/TCOMM.2013.021913.120149},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcom/Leduc-PrimeauHMG13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/XuCM13,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Outlier-Robust {PCA:} The High-Dimensional Case},
journal = {{IEEE} Trans. Inf. Theory},
volume = {59},
number = {1},
pages = {546--572},
year = {2013},
url = {https://doi.org/10.1109/TIT.2012.2212415},
doi = {10.1109/TIT.2012.2212415},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tit/XuCM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/BernsteinMS13,
author = {Andrey Bernstein and
Shie Mannor and
Nahum Shimkin},
editor = {Shai Shalev{-}Shwartz and
Ingo Steinwart},
title = {Opportunistic Strategies for Generalized No-Regret Problems},
booktitle = {{COLT} 2013 - The 26th Annual Conference on Learning Theory, June
12-14, 2013, Princeton University, NJ, {USA}},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {30},
pages = {158--171},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v30/Bernstein13.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/conf/colt/BernsteinMS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/AnavaHMS13,
author = {Oren Anava and
Elad Hazan and
Shie Mannor and
Ohad Shamir},
editor = {Shai Shalev{-}Shwartz and
Ingo Steinwart},
title = {Online Learning for Time Series Prediction},
booktitle = {{COLT} 2013 - The 26th Annual Conference on Learning Theory, June
12-14, 2013, Princeton University, NJ, {USA}},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {30},
pages = {172--184},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v30/Anava13.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/AnavaHMS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/PerchetM13,
author = {Vianney Perchet and
Shie Mannor},
editor = {Shai Shalev{-}Shwartz and
Ingo Steinwart},
title = {Approachability, fast and slow},
booktitle = {{COLT} 2013 - The 26th Annual Conference on Learning Theory, June
12-14, 2013, Princeton University, NJ, {USA}},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {30},
pages = {474--488},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v30/Perchet13.html},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/PerchetM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/TamarCM13,
author = {Aviv Tamar and
Dotan Di Castro and
Shie Mannor},
title = {Temporal Difference Methods for the Variance of the Reward To Go},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {495--503},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/tamar13.html},
timestamp = {Wed, 29 May 2019 08:41:45 +0200},
biburl = {https://dblp.org/rec/conf/icml/TamarCM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/ChenCM13,
author = {Yudong Chen and
Constantine Caramanis and
Shie Mannor},
title = {Robust Sparse Regression under Adversarial Corruption},
booktitle = {Proceedings of the 30th International Conference on Machine Learning,
{ICML} 2013, Atlanta, GA, USA, 16-21 June 2013},
series = {{JMLR} Workshop and Conference Proceedings},
volume = {28},
pages = {774--782},
publisher = {JMLR.org},
year = {2013},
url = {http://proceedings.mlr.press/v28/chen13h.html},
timestamp = {Tue, 10 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/ChenCM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/HallakCM13,
author = {Assaf Hallak and
Dotan Di Castro and
Shie Mannor},
editor = {Inderjit S. Dhillon and
Yehuda Koren and
Rayid Ghani and
Ted E. Senator and
Paul Bradley and
Rajesh Parekh and
Jingrui He and
Robert L. Grossman and
Ramasamy Uthurusamy},
title = {Model selection in markovian processes},
booktitle = {The 19th {ACM} {SIGKDD} International Conference on Knowledge Discovery
and Data Mining, {KDD} 2013, Chicago, IL, USA, August 11-14, 2013},
pages = {374--382},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2487575.2487613},
doi = {10.1145/2487575.2487613},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/kdd/HallakCM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/mobihoc/MillingCMS13,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
editor = {A. Chockalingam and
D. Manjunath and
Massimo Franceschetti and
Leandros Tassiulas},
title = {Detecting epidemics using highly noisy data},
booktitle = {The Fourteenth {ACM} International Symposium on Mobile Ad Hoc Networking
and Computing, MobiHoc '13, Bangalore, India, July 29 - August 01,
2013},
pages = {177--186},
publisher = {{ACM}},
year = {2013},
url = {https://doi.org/10.1145/2491288.2491294},
doi = {10.1145/2491288.2491294},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/mobihoc/MillingCMS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/LimXM13,
author = {Shiau Hong Lim and
Huan Xu and
Shie Mannor},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Reinforcement Learning in Robust Markov Decision Processes},
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 = {701--709},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/0deb1c54814305ca9ad266f53bc82511-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/LimXM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FengXMY13,
author = {Jiashi Feng and
Huan Xu and
Shie Mannor and
Shuicheng Yan},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Online {PCA} for Contaminated Data},
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 = {764--772},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/9a96876e2f8f3dc4f3cf45f02c61c0c1-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/FengXMY13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/VainsencherMX13,
author = {Daniel Vainsencher and
Shie Mannor and
Huan Xu},
editor = {Christopher J. C. Burges and
L{\'{e}}on Bottou and
Zoubin Ghahramani and
Kilian Q. Weinberger},
title = {Learning Multiple Models via Regularized Weighting},
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 = {1977--1985},
year = {2013},
url = {https://proceedings.neurips.cc/paper/2013/hash/9ab0d88431732957a618d4a469a0d4c3-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/VainsencherMX13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-0104,
author = {Aviv Tamar and
Dotan Di Castro and
Shie Mannor},
title = {Policy Evaluation with Variance Related Risk Criteria in Markov Decision
Processes},
journal = {CoRR},
volume = {abs/1301.0104},
year = {2013},
url = {http://arxiv.org/abs/1301.0104},
eprinttype = {arXiv},
eprint = {1301.0104},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-0104.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1301-2725,
author = {Yudong Chen and
Constantine Caramanis and
Shie Mannor},
title = {Robust High Dimensional Sparse Regression and Matching Pursuit},
journal = {CoRR},
volume = {abs/1301.2725},
year = {2013},
url = {http://arxiv.org/abs/1301.2725},
eprinttype = {arXiv},
eprint = {1301.2725},
timestamp = {Tue, 10 Sep 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1301-2725.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1302-6927,
author = {Oren Anava and
Elad Hazan and
Shie Mannor and
Ohad Shamir},
title = {Online Learning for Time Series Prediction},
journal = {CoRR},
volume = {abs/1302.6927},
year = {2013},
url = {http://arxiv.org/abs/1302.6927},
eprinttype = {arXiv},
eprint = {1302.6927},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1302-6927.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1302-6937,
author = {Oren Anava and
Elad Hazan and
Shie Mannor},
title = {Online Learning for Loss Functions with Memory and Applications to
Statistical Arbitrage},
journal = {CoRR},
volume = {abs/1302.6937},
year = {2013},
url = {http://arxiv.org/abs/1302.6937},
eprinttype = {arXiv},
eprint = {1302.6937},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1302-6937.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1305-5399,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
title = {A Primal Condition for Approachability with Partial Monitoring},
journal = {CoRR},
volume = {abs/1305.5399},
year = {2013},
url = {http://arxiv.org/abs/1305.5399},
eprinttype = {arXiv},
eprint = {1305.5399},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1305-5399.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TamarXM13,
author = {Aviv Tamar and
Huan Xu and
Shie Mannor},
title = {Scaling Up Robust MDPs by Reinforcement Learning},
journal = {CoRR},
volume = {abs/1306.6189},
year = {2013},
url = {http://arxiv.org/abs/1306.6189},
eprinttype = {arXiv},
eprint = {1306.6189},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/TamarXM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MeiromMO13,
author = {Eli A. Meirom and
Shie Mannor and
Ariel Orda},
title = {Formation Games and the Internet Structure},
journal = {CoRR},
volume = {abs/1307.4102},
year = {2013},
url = {http://arxiv.org/abs/1307.4102},
eprinttype = {arXiv},
eprint = {1307.4102},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MeiromMO13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/MillingCMS13,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
title = {Distinguishing Infections on Different Graph Topologies},
journal = {CoRR},
volume = {abs/1309.6545},
year = {2013},
url = {http://arxiv.org/abs/1309.6545},
eprinttype = {arXiv},
eprint = {1309.6545},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/MillingCMS13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/TamarM13,
author = {Aviv Tamar and
Shie Mannor},
title = {Variance Adjusted Actor Critic Algorithms},
journal = {CoRR},
volume = {abs/1310.3697},
year = {2013},
url = {http://arxiv.org/abs/1310.3697},
eprinttype = {arXiv},
eprint = {1310.3697},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/TamarM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/GopalanMM13,
author = {Aditya Gopalan and
Shie Mannor and
Yishay Mansour},
title = {Thompson Sampling for Complex Bandit Problems},
journal = {CoRR},
volume = {abs/1311.0466},
year = {2013},
url = {http://arxiv.org/abs/1311.0466},
eprinttype = {arXiv},
eprint = {1311.0466},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/GopalanMM13.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/anor/DanakM12,
author = {Amir Danak and
Shie Mannor},
title = {Approximately optimal bidding policies for repeated first-price auctions},
journal = {Ann. Oper. Res.},
volume = {196},
number = {1},
pages = {189--199},
year = {2012},
url = {https://doi.org/10.1007/s10479-012-1148-8},
doi = {10.1007/S10479-012-1148-8},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/anor/DanakM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ior/XuCM12,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Optimization Under Probabilistic Envelope Constraints},
journal = {Oper. Res.},
volume = {60},
number = {3},
pages = {682--699},
year = {2012},
url = {https://doi.org/10.1287/opre.1120.1054},
doi = {10.1287/OPRE.1120.1054},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ior/XuCM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/XuM12,
author = {Huan Xu and
Shie Mannor},
title = {Robustness and generalization},
journal = {Mach. Learn.},
volume = {86},
number = {3},
pages = {391--423},
year = {2012},
url = {https://doi.org/10.1007/s10994-011-5268-1},
doi = {10.1007/S10994-011-5268-1},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/ml/XuM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/XuCM12,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {A Distributional Interpretation of Robust Optimization},
journal = {Math. Oper. Res.},
volume = {37},
number = {1},
pages = {95--110},
year = {2012},
url = {https://doi.org/10.1287/moor.1110.0531},
doi = {10.1287/MOOR.1110.0531},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mor/XuCM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/XuM12,
author = {Huan Xu and
Shie Mannor},
title = {Distributionally Robust Markov Decision Processes},
journal = {Math. Oper. Res.},
volume = {37},
number = {2},
pages = {288--300},
year = {2012},
url = {https://doi.org/10.1287/moor.1120.0540},
doi = {10.1287/MOOR.1120.0540},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/mor/XuM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/XuCM12,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Sparse Algorithms Are Not Stable: {A} No-Free-Lunch Theorem},
journal = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
volume = {34},
number = {1},
pages = {187--193},
year = {2012},
url = {https://doi.org/10.1109/TPAMI.2011.177},
doi = {10.1109/TPAMI.2011.177},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/pami/XuCM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcom/Leduc-PrimeauHMG12,
author = {Fran{\c{c}}ois Leduc{-}Primeau and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Dithered Belief Propagation Decoding},
journal = {{IEEE} Trans. Commun.},
volume = {60},
number = {8},
pages = {2042--2047},
year = {2012},
url = {https://doi.org/10.1109/TCOMM.2012.050812.110115A},
doi = {10.1109/TCOMM.2012.050812.110115A},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcom/Leduc-PrimeauHMG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/MillingCMS12,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
title = {On identifying the causative network of an epidemic},
booktitle = {50th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2012, Allerton Park {\&} Retreat Center, Monticello,
IL, USA, October 1-5, 2012},
pages = {909--914},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/Allerton.2012.6483315},
doi = {10.1109/ALLERTON.2012.6483315},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/allerton/MillingCMS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/KizilkaleMC12,
author = {Arman C. Kizilkale and
Shie Mannor and
Peter E. Caines},
title = {Large scale real-time bidding in the smart grid: {A} mean field framework},
booktitle = {Proceedings of the 51th {IEEE} Conference on Decision and Control,
{CDC} 2012, December 10-13, 2012, Maui, HI, {USA}},
pages = {3680--3687},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/CDC.2012.6425895},
doi = {10.1109/CDC.2012.6425895},
timestamp = {Fri, 04 Mar 2022 13:28:47 +0100},
biburl = {https://dblp.org/rec/conf/cdc/KizilkaleMC12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/KizilkaleM12,
author = {Arman C. Kizilkale and
Shie Mannor},
title = {Duality of ancillary services and intermittent suppliers},
booktitle = {Proceedings of the 51th {IEEE} Conference on Decision and Control,
{CDC} 2012, December 10-13, 2012, Maui, HI, {USA}},
pages = {4977--4984},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/CDC.2012.6426759},
doi = {10.1109/CDC.2012.6426759},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/KizilkaleM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/AvnerMS12,
author = {Orly Avner and
Shie Mannor and
Ohad Shamir},
title = {Decoupling Exploration and Exploitation in Multi-Armed Bandits},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/230.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/AvnerMS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/CastroTM12,
author = {Dotan Di Castro and
Aviv Tamar and
Shie Mannor},
title = {Policy Gradients with Variance Related Risk Criteria},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/489.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/CastroTM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorMX12,
author = {Shie Mannor and
Ofir Mebel and
Huan Xu},
title = {Lightning Does Not Strike Twice: Robust MDPs with Coupled Uncertainty},
booktitle = {Proceedings of the 29th International Conference on Machine Learning,
{ICML} 2012, Edinburgh, Scotland, UK, June 26 - July 1, 2012},
publisher = {icml.cc / Omnipress},
year = {2012},
url = {http://icml.cc/2012/papers/215.pdf},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MannorMX12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/HarelM12,
author = {Maayan Harel and
Shie Mannor},
editor = {Peter L. Bartlett and
Fernando C. N. Pereira and
Christopher J. C. Burges and
L{\'{e}}on Bottou and
Kilian Q. Weinberger},
title = {The Perturbed Variation},
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 = {1943--1951},
year = {2012},
url = {https://proceedings.neurips.cc/paper/2012/hash/168908dd3227b8358eababa07fcaf091-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/HarelM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sigmetrics/MillingCMS12,
author = {Chris Milling and
Constantine Caramanis and
Shie Mannor and
Sanjay Shakkottai},
editor = {Peter G. Harrison and
Martin F. Arlitt and
Giuliano Casale},
title = {Network forensics: random infection vs spreading epidemic},
booktitle = {{ACM} {SIGMETRICS/PERFORMANCE} Joint International Conference on Measurement
and Modeling of Computer Systems, {SIGMETRICS} '12, London, United
Kingdom, June 11-15, 2012},
pages = {223--234},
publisher = {{ACM}},
year = {2012},
url = {https://doi.org/10.1145/2254756.2254784},
doi = {10.1145/2254756.2254784},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sigmetrics/MillingCMS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sips/TehraniSMG12,
author = {Saeed Sharifi Tehrani and
Paul H. Siegel and
Shie Mannor and
Warren J. Gross},
title = {Joint Stochastic Decoding of {LDPC} Codes and Partial-Response Channels},
booktitle = {2012 {IEEE} Workshop on Signal Processing Systems, Quebec City, QC,
Canada, October 17-19, 2012},
pages = {13--18},
publisher = {{IEEE}},
year = {2012},
url = {https://doi.org/10.1109/SiPS.2012.55},
doi = {10.1109/SIPS.2012.55},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sips/TehraniSMG12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/MannorS12,
author = {Shie Mannor and
Nathan Srebro},
editor = {Shie Mannor and
Nathan Srebro and
Robert C. Williamson},
title = {Preface},
booktitle = {{COLT} 2012 - The 25th Annual Conference on Learning Theory, June
25-27, 2012, Edinburgh, Scotland},
series = {{JMLR} Proceedings},
volume = {23},
pages = {1.1--1.2},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v23/mannor12/mannor12.pdf},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorS12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/HaimovitchCM12,
author = {Yoav Haimovitch and
Koby Crammer and
Shie Mannor},
editor = {Steven C. H. Hoi and
Wray L. Buntine},
title = {More Is Better: Large Scale Partially-supervised Sentiment Classication},
booktitle = {Proceedings of the 4th Asian Conference on Machine Learning, {ACML}
2012, Singapore, Singapore, November 4-6, 2012},
series = {{JMLR} Proceedings},
volume = {25},
pages = {175--190},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v25/haimovitch12.html},
timestamp = {Wed, 29 May 2019 08:41:47 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/HaimovitchCM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/XuCM12,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
editor = {Neil D. Lawrence and
Mark A. Girolami},
title = {Statistical Optimization in High Dimensions},
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 = {1332--1340},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v22/xu12a.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/XuCM12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:books/sp/12/VlassisGMP12,
author = {Nikos Vlassis and
Mohammad Ghavamzadeh and
Shie Mannor and
Pascal Poupart},
editor = {Marco A. Wiering and
Martijn van Otterlo},
title = {Bayesian Reinforcement Learning},
booktitle = {Reinforcement Learning},
series = {Adaptation, Learning, and Optimization},
volume = {12},
pages = {359--386},
publisher = {Springer},
year = {2012},
url = {https://doi.org/10.1007/978-3-642-27645-3\_11},
doi = {10.1007/978-3-642-27645-3\_11},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/books/sp/12/VlassisGMP12.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@proceedings{DBLP:conf/colt/2012,
editor = {Shie Mannor and
Nathan Srebro and
Robert C. Williamson},
title = {{COLT} 2012 - The 25th Annual Conference on Learning Theory, June
25-27, 2012, Edinburgh, Scotland},
series = {{JMLR} Proceedings},
volume = {23},
publisher = {JMLR.org},
year = {2012},
url = {http://proceedings.mlr.press/v23/},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/2012.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-2428,
author = {Fran{\c{c}}ois Leduc{-}Primeau and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Relaxed Half-Stochastic Belief Propagation},
journal = {CoRR},
volume = {abs/1205.2428},
year = {2012},
url = {http://arxiv.org/abs/1205.2428},
eprinttype = {arXiv},
eprint = {1205.2428},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-2428.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1205-2874,
author = {Orly Avner and
Shie Mannor and
Ohad Shamir},
title = {Decoupling Exploration and Exploitation in Multi-Armed Bandits},
journal = {CoRR},
volume = {abs/1205.2874},
year = {2012},
url = {http://arxiv.org/abs/1205.2874},
eprinttype = {arXiv},
eprint = {1205.2874},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1205-2874.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-4169,
author = {Loc Bui and
Ramesh Johari and
Shie Mannor},
title = {Clustered Bandits},
journal = {CoRR},
volume = {abs/1206.4169},
year = {2012},
url = {http://arxiv.org/abs/1206.4169},
eprinttype = {arXiv},
eprint = {1206.4169},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-4169.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1206-4643,
author = {Shie Mannor and
Ofir Mebel and
Huan Xu},
title = {Lightning Does Not Strike Twice: Robust MDPs with Coupled Uncertainty},
journal = {CoRR},
volume = {abs/1206.4643},
year = {2012},
url = {http://arxiv.org/abs/1206.4643},
eprinttype = {arXiv},
eprint = {1206.4643},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1206-4643.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1208-2417,
author = {Assaf Hallak and
Shie Mannor},
title = {How to sample if you must: on optimal functional sampling},
journal = {CoRR},
volume = {abs/1208.2417},
year = {2012},
url = {http://arxiv.org/abs/1208.2417},
eprinttype = {arXiv},
eprint = {1208.2417},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1208-2417.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1209-6329,
author = {Yoav Haimovitch and
Koby Crammer and
Shie Mannor},
title = {More Is Better: Large Scale Partially-supervised Sentiment Classification
- Appendix},
journal = {CoRR},
volume = {abs/1209.6329},
year = {2012},
url = {http://arxiv.org/abs/1209.6329},
eprinttype = {arXiv},
eprint = {1209.6329},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1209-6329.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1210-4006,
author = {Maayan Harel and
Shie Mannor},
title = {The Perturbed Variation},
journal = {CoRR},
volume = {abs/1210.4006},
year = {2012},
url = {http://arxiv.org/abs/1210.4006},
eprinttype = {arXiv},
eprint = {1210.4006},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1210-4006.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/VainsencherMB11a,
author = {Daniel Vainsencher and
Shie Mannor and
Alfred M. Bruckstein},
title = {The Sample Complexity of Dictionary Learning},
journal = {J. Mach. Learn. Res.},
volume = {12},
pages = {3259--3281},
year = {2011},
url = {https://dl.acm.org/doi/10.5555/1953048.2078210},
doi = {10.5555/1953048.2078210},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/VainsencherMB11a.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tciaig/DanakM11,
author = {Amir Danak and
Shie Mannor},
title = {A Robust Learning Approach to Repeated Auctions With Monitoring and
Entry Fees},
journal = {{IEEE} Trans. Comput. Intell. {AI} Games},
volume = {3},
number = {4},
pages = {302--315},
year = {2011},
url = {https://doi.org/10.1109/TCIAIG.2011.2160994},
doi = {10.1109/TCIAIG.2011.2160994},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tciaig/DanakM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tpds/DanakM11,
author = {Amir Danak and
Shie Mannor},
title = {Efficient Bidding in Dynamic Grid Markets},
journal = {{IEEE} Trans. Parallel Distributed Syst.},
volume = {22},
number = {9},
pages = {1483--1496},
year = {2011},
url = {https://doi.org/10.1109/TPDS.2011.29},
doi = {10.1109/TPDS.2011.29},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tpds/DanakM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/NaderiMSG11,
author = {Ali Naderi and
Shie Mannor and
Mohamad Sawan and
Warren J. Gross},
title = {Delayed Stochastic Decoding of {LDPC} Codes},
journal = {{IEEE} Trans. Signal Process.},
volume = {59},
number = {11},
pages = {5617--5626},
year = {2011},
url = {https://doi.org/10.1109/TSP.2011.2163630},
doi = {10.1109/TSP.2011.2163630},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/NaderiMSG11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/vlsisp/TehraniNKMG11,
author = {Saeed Sharifi Tehrani and
Ali Naderi and
Guy{-}Armand Kamendje and
Shie Mannor and
Warren J. Gross},
title = {Tracking Forecast Memories for Stochastic Decoding},
journal = {J. Signal Process. Syst.},
volume = {63},
number = {1},
pages = {117--127},
year = {2011},
url = {https://doi.org/10.1007/s11265-009-0441-5},
doi = {10.1007/S11265-009-0441-5},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/vlsisp/TehraniNKMG11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaaiss/FrankMP11,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
title = {Activity Recognition with Time-Delay Emobeddings},
booktitle = {Computational Physiology, Papers from the 2011 {AAAI} Spring Symposium,
Technical Report SS-11-04, Stanford, California, USA, March 21-23,
2011},
publisher = {{AAAI}},
year = {2011},
url = {http://www.aaai.org/ocs/index.php/SSS/SSS11/paper/view/2446},
timestamp = {Mon, 13 Feb 2012 17:06:00 +0100},
biburl = {https://dblp.org/rec/conf/aaaiss/FrankMP11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/KizilkaleM11,
author = {Arman C. Kizilkale and
Shie Mannor},
title = {Regulation and double price mechanisms in markets with friction},
booktitle = {50th {IEEE} Conference on Decision and Control and European Control
Conference, 11th European Control Conference, {CDC/ECC} 2011, Orlando,
FL, USA, December 12-15, 2011},
pages = {33--40},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/CDC.2011.6161107},
doi = {10.1109/CDC.2011.6161107},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/KizilkaleM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/AvnerM11,
author = {Orly Avner and
Shie Mannor},
title = {Stochastic bandits with pathwise constraints},
booktitle = {50th {IEEE} Conference on Decision and Control and European Control
Conference, 11th European Control Conference, {CDC/ECC} 2011, Orlando,
FL, USA, December 12-15, 2011},
pages = {3862--3869},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/CDC.2011.6161093},
doi = {10.1109/CDC.2011.6161093},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/AvnerM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/YuM11,
author = {Jia Yuan Yu and
Shie Mannor},
editor = {Lise Getoor and
Tobias Scheffer},
title = {Unimodal Bandits},
booktitle = {Proceedings of the 28th International Conference on Machine Learning,
{ICML} 2011, Bellevue, Washington, USA, June 28 - July 2, 2011},
pages = {41--48},
publisher = {Omnipress},
year = {2011},
url = {https://icml.cc/2011/papers/50\_icmlpaper.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/YuM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorT11,
author = {Shie Mannor and
John N. Tsitsiklis},
editor = {Lise Getoor and
Tobias Scheffer},
title = {Mean-Variance Optimization in Markov Decision Processes},
booktitle = {Proceedings of the 28th International Conference on Machine Learning,
{ICML} 2011, Bellevue, Washington, USA, June 28 - July 2, 2011},
pages = {177--184},
publisher = {Omnipress},
year = {2011},
url = {https://icml.cc/2011/papers/156\_icmlpaper.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MannorT11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/HarelM11,
author = {Maayan Harel and
Shie Mannor},
editor = {Lise Getoor and
Tobias Scheffer},
title = {Learning from Multiple Outlooks},
booktitle = {Proceedings of the 28th International Conference on Machine Learning,
{ICML} 2011, Bellevue, Washington, USA, June 28 - July 2, 2011},
pages = {401--408},
publisher = {Omnipress},
year = {2011},
url = {https://icml.cc/2011/papers/275\_icmlpaper.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/HarelM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/VainsencherDM11,
author = {Daniel Vainsencher and
Ofer Dekel and
Shie Mannor},
editor = {Lise Getoor and
Tobias Scheffer},
title = {Bundle Selling by Online Estimation of Valuation Functions},
booktitle = {Proceedings of the 28th International Conference on Machine Learning,
{ICML} 2011, Bellevue, Washington, USA, June 28 - July 2, 2011},
pages = {1137--1144},
publisher = {Omnipress},
year = {2011},
url = {https://icml.cc/2011/papers/582\_icmlpaper.pdf},
timestamp = {Wed, 03 Apr 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/VainsencherDM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ijcai/XuM11,
author = {Huan Xu and
Shie Mannor},
editor = {Toby Walsh},
title = {Probabilistic Goal Markov Decision Processes},
booktitle = {{IJCAI} 2011, Proceedings of the 22nd International Joint Conference
on Artificial Intelligence, Barcelona, Catalonia, Spain, July 16-22,
2011},
pages = {2046--2052},
publisher = {{IJCAI/AAAI}},
year = {2011},
url = {https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-341},
doi = {10.5591/978-1-57735-516-8/IJCAI11-341},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ijcai/XuM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/JagannathanMMM11,
author = {Krishna P. Jagannathan and
Shie Mannor and
Ishai Menache and
Eytan H. Modiano},
title = {A state action frequency approach to throughput maximization over
uncertain wireless channels},
booktitle = {{INFOCOM} 2011. 30th {IEEE} International Conference on Computer Communications,
Joint Conference of the {IEEE} Computer and Communications Societies,
10-15 April 2011, Shanghai, China},
pages = {491--495},
publisher = {{IEEE}},
year = {2011},
url = {https://doi.org/10.1109/INFCOM.2011.5935211},
doi = {10.1109/INFCOM.2011.5935211},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/infocom/JagannathanMMM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MannorS11,
author = {Shie Mannor and
Ohad Shamir},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {From Bandits to Experts: On the Value of Side-Observations},
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 = {684--692},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/e1e32e235eee1f970470a3a6658dfdd5-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MannorS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BuiJM11,
author = {Loc Bui and
Ramesh Johari and
Shie Mannor},
editor = {John Shawe{-}Taylor and
Richard S. Zemel and
Peter L. Bartlett and
Fernando C. N. Pereira and
Kilian Q. Weinberger},
title = {Committing Bandits},
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 = {1557--1565},
year = {2011},
url = {https://proceedings.neurips.cc/paper/2011/hash/d56b9fc4b0f1be8871f5e1c40c0067e7-Abstract.html},
timestamp = {Thu, 21 Jan 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/BuiJM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/FrankMP11,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
editor = {Dimitrios Gunopulos and
Thomas Hofmann and
Donato Malerba and
Michalis Vazirgiannis},
title = {Activity Recognition with Mobile Phones},
booktitle = {Machine Learning and Knowledge Discovery in Databases - European Conference,
{ECML} {PKDD} 2011, Athens, Greece, September 5-9, 2011, Proceedings,
Part {III}},
series = {Lecture Notes in Computer Science},
volume = {6913},
pages = {630--633},
publisher = {Springer},
year = {2011},
url = {https://doi.org/10.1007/978-3-642-23808-6\_44},
doi = {10.1007/978-3-642-23808-6\_44},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/FrankMP11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/MannorPS11,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Robust approachability and regret minimization in games with partial
monitoring},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {515--536},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/mannor11a/mannor11a.pdf},
timestamp = {Wed, 29 May 2019 08:41:47 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorPS11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/VainsencherMB11,
author = {Daniel Vainsencher and
Shie Mannor and
Alfred M. Bruckstein},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {The Sample Complexity of Dictionary Learning},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {773--788},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/vainsencher11a/vainsencher11a.pdf},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/VainsencherMB11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:journals/jmlr/AbernethyM11,
author = {Jacob D. Abernethy and
Shie Mannor},
editor = {Sham M. Kakade and
Ulrike von Luxburg},
title = {Does an Efficient Calibrated Forecasting Strategy Exist?},
booktitle = {{COLT} 2011 - The 24th Annual Conference on Learning Theory, June
9-11, 2011, Budapest, Hungary},
series = {{JMLR} Proceedings},
volume = {19},
pages = {809--812},
publisher = {JMLR.org},
year = {2011},
url = {http://proceedings.mlr.press/v19/abernethy11a/abernethy11a.pdf},
timestamp = {Wed, 29 May 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/AbernethyM11.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1104-5601,
author = {Shie Mannor and
John N. Tsitsiklis},
title = {Mean-Variance Optimization in Markov Decision Processes},
journal = {CoRR},
volume = {abs/1104.5601},
year = {2011},
url = {http://arxiv.org/abs/1104.5601},
eprinttype = {arXiv},
eprint = {1104.5601},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1104-5601.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1105-4995,
author = {Shie Mannor and
Vianney Perchet and
Gilles Stoltz},
title = {Robust approachability and regret minimization in games with partial
monitoring},
journal = {CoRR},
volume = {abs/1105.4995},
year = {2011},
url = {http://arxiv.org/abs/1105.4995},
eprinttype = {arXiv},
eprint = {1105.4995},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1105-4995.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1106-2436,
author = {Shie Mannor and
Ohad Shamir},
title = {From Bandits to Experts: On the Value of Side-Observations},
journal = {CoRR},
volume = {abs/1106.2436},
year = {2011},
url = {http://arxiv.org/abs/1106.2436},
eprinttype = {arXiv},
eprint = {1106.2436},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1106-2436.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1109-2296,
author = {Dotan Di Castro and
Claudio Gentile and
Shie Mannor},
title = {Bandits with an Edge},
journal = {CoRR},
volume = {abs/1109.2296},
year = {2011},
url = {http://arxiv.org/abs/1109.2296},
eprinttype = {arXiv},
eprint = {1109.2296},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1109-2296.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1109-3151,
author = {Arman C. Kizilkale and
Shie Mannor},
title = {Regulation, Volatility and Efficiency in Continuous-Time Markets},
journal = {CoRR},
volume = {abs/1109.3151},
year = {2011},
url = {http://arxiv.org/abs/1109.3151},
eprinttype = {arXiv},
eprint = {1109.3151},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1109-3151.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/icl/LerouxHMG10,
author = {Camille Leroux and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Stochastic Chase Decoding of Reed-Solomon Codes},
journal = {{IEEE} Commun. Lett.},
volume = {14},
number = {9},
pages = {863--865},
year = {2010},
url = {https://doi.org/10.1109/LCOMM.2010.09.100594},
doi = {10.1109/LCOMM.2010.09.100594},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/icl/LerouxHMG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ior/DelageM10,
author = {Erick Delage and
Shie Mannor},
title = {Percentile Optimization for Markov Decision Processes with Parameter
Uncertainty},
journal = {Oper. Res.},
volume = {58},
number = {1},
pages = {203--213},
year = {2010},
url = {https://doi.org/10.1287/opre.1080.0685},
doi = {10.1287/OPRE.1080.0685},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ior/DelageM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/MannorS10,
author = {Shie Mannor and
Gilles Stoltz},
title = {A Geometric Proof of Calibration},
journal = {Math. Oper. Res.},
volume = {35},
number = {4},
pages = {721--727},
year = {2010},
url = {https://doi.org/10.1287/moor.1100.0465},
doi = {10.1287/MOOR.1100.0465},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/MannorS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcas/CushonLHMG10,
author = {Kevin Cushon and
Camille Leroux and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {A Min-Sum Iterative Decoder Based on Pulsewidth Message Encoding},
journal = {{IEEE} Trans. Circuits Syst. {II} Express Briefs},
volume = {57-II},
number = {11},
pages = {893--897},
year = {2010},
url = {https://doi.org/10.1109/TCSII.2010.2082970},
doi = {10.1109/TCSII.2010.2082970},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tcas/CushonLHMG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/XuCM10,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Robust regression and Lasso},
journal = {{IEEE} Trans. Inf. Theory},
volume = {56},
number = {7},
pages = {3561--3574},
year = {2010},
url = {https://doi.org/10.1109/TIT.2010.2048503},
doi = {10.1109/TIT.2010.2048503},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tit/XuCM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/TehraniNKHMG10,
author = {Saeed Sharifi Tehrani and
Ali Naderi and
Guy{-}Armand Kamendje and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Majority-based tracking forecast memories for stochastic {LDPC} decoding},
journal = {{IEEE} Trans. Signal Process.},
volume = {58},
number = {9},
pages = {4883--4896},
year = {2010},
url = {https://doi.org/10.1109/TSP.2010.2051434},
doi = {10.1109/TSP.2010.2051434},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/TehraniNKHMG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/TehraniWGMHG10,
author = {Saeed Sharifi Tehrani and
Chris Winstead and
Warren J. Gross and
Shie Mannor and
Sheryl L. Howard and
Vincent C. Gaudet},
title = {Relaxation dynamics in stochastic iterative decoders},
journal = {{IEEE} Trans. Signal Process.},
volume = {58},
number = {11},
pages = {5955--5961},
year = {2010},
url = {https://doi.org/10.1109/TSP.2010.2066269},
doi = {10.1109/TSP.2010.2066269},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/TehraniWGMHG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/FrankMP10,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
editor = {Maria Fox and
David Poole},
title = {Activity and Gait Recognition with Time-Delay Embeddings},
booktitle = {Proceedings of the Twenty-Fourth {AAAI} Conference on Artificial Intelligence,
{AAAI} 2010, Atlanta, Georgia, USA, July 11-15, 2010},
pages = {1581--1586},
publisher = {{AAAI} Press},
year = {2010},
url = {https://doi.org/10.1609/aaai.v24i1.7724},
doi = {10.1609/AAAI.V24I1.7724},
timestamp = {Mon, 04 Sep 2023 16:23:45 +0200},
biburl = {https://dblp.org/rec/conf/aaai/FrankMP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/SarkisHMG10,
author = {Gabi Sarkis and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Relaxed half-stochastic decoding of {LDPC} codes over GF(q)},
booktitle = {48th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020},
pages = {36--41},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ALLERTON.2010.5706885},
doi = {10.1109/ALLERTON.2010.5706885},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/SarkisHMG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/KizilkaleM10,
author = {Arman C. Kizilkale and
Shie Mannor},
title = {Volatility and efficiency in markets with friction},
booktitle = {48th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020},
pages = {50--57},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ALLERTON.2010.5706887},
doi = {10.1109/ALLERTON.2010.5706887},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/KizilkaleM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/XuCM10,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {A distributional interpretation of robust optimization},
booktitle = {48th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020},
pages = {552--556},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ALLERTON.2010.5706955},
doi = {10.1109/ALLERTON.2010.5706955},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/XuCM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/CastroM10,
author = {Dotan Di Castro and
Shie Mannor},
title = {Tutor learning using linear constraints in approximate dynamic programming},
booktitle = {48th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2010, Monticello, IL, USA, September 29 - October 1, 2020},
pages = {1384--1390},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/ALLERTON.2010.5707075},
doi = {10.1109/ALLERTON.2010.5707075},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/CastroM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/KizilkaleM10,
author = {Arman C. Kizilkale and
Shie Mannor},
title = {Regulation and efficiency in markets with friction},
booktitle = {Proceedings of the 49th {IEEE} Conference on Decision and Control,
{CDC} 2010, December 15-17, 2010, Atlanta, Georgia, {USA}},
pages = {4137--4144},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/CDC.2010.5717446},
doi = {10.1109/CDC.2010.5717446},
timestamp = {Fri, 04 Mar 2022 13:28:01 +0100},
biburl = {https://dblp.org/rec/conf/cdc/KizilkaleM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/CastroM10,
author = {Dotan Di Castro and
Shie Mannor},
title = {Adaptive bases for Q-learning},
booktitle = {Proceedings of the 49th {IEEE} Conference on Decision and Control,
{CDC} 2010, December 15-17, 2010, Atlanta, Georgia, {USA}},
pages = {4587--4593},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/CDC.2010.5717385},
doi = {10.1109/CDC.2010.5717385},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/CastroM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/Even-DarMM10,
author = {Eyal Even{-}Dar and
Shie Mannor and
Yishay Mansour},
editor = {Adam Tauman Kalai and
Mehryar Mohri},
title = {Learning with Global Cost in Stochastic Environments},
booktitle = {{COLT} 2010 - The 23rd Conference on Learning Theory, Haifa, Israel,
June 27-29, 2010},
pages = {80--92},
publisher = {Omnipress},
year = {2010},
url = {http://colt2010.haifa.il.ibm.com/papers/COLT2010proceedings.pdf\#page=88},
timestamp = {Tue, 25 Jan 2022 13:23:33 +0100},
biburl = {https://dblp.org/rec/conf/colt/Even-DarMM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/XuCM10,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
editor = {Adam Tauman Kalai and
Mehryar Mohri},
title = {Principal Component Analysis with Contaminated Data: The High Dimensional
Case},
booktitle = {{COLT} 2010 - The 23rd Conference on Learning Theory, Haifa, Israel,
June 27-29, 2010},
pages = {490--502},
publisher = {Omnipress},
year = {2010},
url = {http://colt2010.haifa.il.ibm.com/papers/COLT2010proceedings.pdf\#page=498},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/XuCM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/XuM10,
author = {Huan Xu and
Shie Mannor},
editor = {Adam Tauman Kalai and
Mehryar Mohri},
title = {Robustness and Generalization},
booktitle = {{COLT} 2010 - The 23rd Conference on Learning Theory, Haifa, Israel,
June 27-29, 2010},
pages = {503--515},
publisher = {Omnipress},
year = {2010},
url = {http://colt2010.haifa.il.ibm.com/papers/COLT2010proceedings.pdf\#page=511},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/XuM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/globecom/Leduc-PrimeauHMG10,
author = {Fran{\c{c}}ois Leduc{-}Primeau and
Saied Hemati and
Shie Mannor and
Warren J. Gross},
title = {Lowering Error Floors Using Dithered Belief Propagation},
booktitle = {Proceedings of the Global Communications Conference, 2010. {GLOBECOM}
2010, 6-10 December 2010, Miami, Florida, {USA}},
pages = {1--6},
publisher = {{IEEE}},
year = {2010},
url = {https://doi.org/10.1109/GLOCOM.2010.5683799},
doi = {10.1109/GLOCOM.2010.5683799},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/globecom/Leduc-PrimeauHMG10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/huc/FrankMP10,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
editor = {Jakob E. Bardram and
Marc Langheinrich and
Khai N. Truong and
Paddy Nixon},
title = {A novel similarity measure for time series data with applications
to gait and activity recognition},
booktitle = {UbiComp 2010: Ubiquitous Computing, 12th International Conference,
UbiComp 2010, Copenhagen, Denmark, September 26-29, 2010, Adjunct
Papers Proceedings},
series = {{ACM} International Conference Proceeding Series},
pages = {407--408},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1864431.1864460},
doi = {10.1145/1864431.1864460},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/huc/FrankMP10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icdcs/DanakM10,
author = {Amir Danak and
Shie Mannor},
title = {Resource Allocation with Supply Adjustment in Distributed Computing
Systems},
booktitle = {2010 International Conference on Distributed Computing Systems, {ICDCS}
2010, Genova, Italy, June 21-25, 2010},
pages = {498--506},
publisher = {{IEEE} Computer Society},
year = {2010},
url = {https://doi.org/10.1109/ICDCS.2010.60},
doi = {10.1109/ICDCS.2010.60},
timestamp = {Fri, 24 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icdcs/DanakM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/kdd/DyagilevMY10,
author = {Kirill Dyagilev and
Shie Mannor and
Elad Yom{-}Tov},
editor = {Prem Melville and
Jure Leskovec and
Foster J. Provost},
title = {Generative models for rapid information propagation},
booktitle = {Proceedings of the First Workshop on Social Media Analytics, SOMA@KDD
2010, Washington, DC, USA, July 25, 2010},
pages = {35--43},
publisher = {{ACM}},
year = {2010},
url = {https://doi.org/10.1145/1964858.1964864},
doi = {10.1145/1964858.1964864},
timestamp = {Thu, 22 Dec 2022 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/kdd/DyagilevMY10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BernsteinMS10,
author = {Andrey Bernstein and
Shie Mannor and
Nahum Shimkin},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Online Classification with Specificity Constraints},
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 = {190--198},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/9cfdf10e8fc047a44b08ed031e1f0ed1-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/BernsteinMS10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuM10,
author = {Huan Xu and
Shie Mannor},
editor = {John D. Lafferty and
Christopher K. I. Williams and
John Shawe{-}Taylor and
Richard S. Zemel and
Aron Culotta},
title = {Distributionally Robust Markov Decision Processes},
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 = {2505--2513},
publisher = {Curran Associates, Inc.},
year = {2010},
url = {https://proceedings.neurips.cc/paper/2010/hash/19f3cd308f1455b3fa09a282e0d496f4-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/XuM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/pkdd/CastroM10,
author = {Dotan Di Castro and
Shie Mannor},
editor = {Jos{\'{e}} L. Balc{\'{a}}zar and
Francesco Bonchi and
Aristides Gionis and
Mich{\`{e}}le Sebag},
title = {Adaptive Bases for Reinforcement Learning},
booktitle = {Machine Learning and Knowledge Discovery in Databases, European Conference,
{ECML} {PKDD} 2010, Barcelona, Spain, September 20-24, 2010, Proceedings,
Part {I}},
series = {Lecture Notes in Computer Science},
volume = {6321},
pages = {312--327},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-3-642-15880-3\_26},
doi = {10.1007/978-3-642-15880-3\_26},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/pkdd/CastroM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@incollection{DBLP:reference/ml/Mannor10,
author = {Shie Mannor},
editor = {Claude Sammut and
Geoffrey I. Webb},
title = {\emph{k}-Armed Bandit},
booktitle = {Encyclopedia of Machine Learning},
pages = {561--563},
publisher = {Springer},
year = {2010},
url = {https://doi.org/10.1007/978-0-387-30164-8\_424},
doi = {10.1007/978-0-387-30164-8\_424},
timestamp = {Wed, 14 Nov 2018 10:51:34 +0100},
biburl = {https://dblp.org/rec/reference/ml/Mannor10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/XuCM10,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Principal Component Analysis with Contaminated Data: The High Dimensional
Case},
journal = {CoRR},
volume = {abs/1002.4658},
year = {2010},
url = {http://arxiv.org/abs/1002.4658},
eprinttype = {arXiv},
eprint = {1002.4658},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/XuCM10.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1005-0027,
author = {Maayan Gal{-}on and
Shie Mannor},
title = {Learning from Multiple Outlooks},
journal = {CoRR},
volume = {abs/1005.0027},
year = {2010},
url = {http://arxiv.org/abs/1005.0027},
eprinttype = {arXiv},
eprint = {1005.0027},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1005-0027.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1005-0125,
author = {Dotan Di Castro and
Shie Mannor},
title = {Adaptive Bases for Reinforcement Learning},
journal = {CoRR},
volume = {abs/1005.0125},
year = {2010},
url = {http://arxiv.org/abs/1005.0125},
eprinttype = {arXiv},
eprint = {1005.0125},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1005-0125.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1005-2243,
author = {Huan Xu and
Shie Mannor},
title = {Robustness and Generalization},
journal = {CoRR},
volume = {abs/1005.2243},
year = {2010},
url = {http://arxiv.org/abs/1005.2243},
eprinttype = {arXiv},
eprint = {1005.2243},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1005-2243.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1011-5395,
author = {Daniel Vainsencher and
Shie Mannor and
Alfred M. Bruckstein},
title = {The Sample Complexity of Dictionary Learning},
journal = {CoRR},
volume = {abs/1011.5395},
year = {2010},
url = {http://arxiv.org/abs/1011.5395},
eprinttype = {arXiv},
eprint = {1011.5395},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1011-5395.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/geb/MannorT09,
author = {Shie Mannor and
John N. Tsitsiklis},
title = {Approachability in repeated games: Computational aspects and a Stackelberg
variant},
journal = {Games Econ. Behav.},
volume = {66},
number = {1},
pages = {315--325},
year = {2009},
url = {https://doi.org/10.1016/j.geb.2008.03.008},
doi = {10.1016/J.GEB.2008.03.008},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/geb/MannorT09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MannorTY09,
author = {Shie Mannor and
John N. Tsitsiklis and
Jia Yuan Yu},
title = {Online Learning with Sample Path Constraints},
journal = {J. Mach. Learn. Res.},
volume = {10},
pages = {569--590},
year = {2009},
url = {https://dl.acm.org/doi/10.5555/1577069.1577089},
doi = {10.5555/1577069.1577089},
timestamp = {Thu, 02 Jun 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorTY09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/XuCM09,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Robustness and Regularization of Support Vector Machines},
journal = {J. Mach. Learn. Res.},
volume = {10},
pages = {1485--1510},
year = {2009},
url = {https://dl.acm.org/doi/10.5555/1577069.1755834},
doi = {10.5555/1577069.1755834},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/jmlr/XuCM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/YuMS09,
author = {Jia Yuan Yu and
Shie Mannor and
Nahum Shimkin},
title = {Markov Decision Processes with Arbitrary Reward Processes},
journal = {Math. Oper. Res.},
volume = {34},
number = {3},
pages = {737--757},
year = {2009},
url = {https://doi.org/10.1287/moor.1090.0397},
doi = {10.1287/MOOR.1090.0397},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/YuMS09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/XuM09,
author = {Huan Xu and
Shie Mannor},
title = {A Kalman Filter Design Based on the Performance/Robustness Tradeoff},
journal = {{IEEE} Trans. Autom. Control.},
volume = {54},
number = {5},
pages = {1171--1175},
year = {2009},
url = {https://doi.org/10.1109/TAC.2009.2017816},
doi = {10.1109/TAC.2009.2017816},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/tac/XuM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/ArcauteJM09,
author = {Esteban Arcaute and
Ramesh Johari and
Shie Mannor},
title = {Network Formation: Bilateral Contracting and Myopic Dynamics},
journal = {{IEEE} Trans. Autom. Control.},
volume = {54},
number = {8},
pages = {1765--1778},
year = {2009},
url = {https://doi.org/10.1109/TAC.2009.2024564},
doi = {10.1109/TAC.2009.2024564},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/ArcauteJM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amcc/FarahmandGSM09,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
title = {Regularized Fitted Q-Iteration for planning in continuous-space Markovian
decision problems},
booktitle = {American Control Conference, {ACC} 2009. St. Louis, Missouri, USA,
June 10-12, 2009},
pages = {725--730},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ACC.2009.5160611},
doi = {10.1109/ACC.2009.5160611},
timestamp = {Fri, 03 Dec 2021 13:02:58 +0100},
biburl = {https://dblp.org/rec/conf/amcc/FarahmandGSM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/YuM09,
author = {Jia Yuan Yu and
Shie Mannor},
title = {Arbitrarily modulated Markov decision processes},
booktitle = {Proceedings of the 48th {IEEE} Conference on Decision and Control,
{CDC} 2009, combined withe the 28th Chinese Control Conference, December
16-18, 2009, Shanghai, China},
pages = {2946--2953},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/CDC.2009.5400662},
doi = {10.1109/CDC.2009.5400662},
timestamp = {Fri, 04 Mar 2022 13:27:41 +0100},
biburl = {https://dblp.org/rec/conf/cdc/YuM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/XuM09,
author = {Huan Xu and
Shie Mannor},
title = {Parametric regret in uncertain Markov decision processes},
booktitle = {Proceedings of the 48th {IEEE} Conference on Decision and Control,
{CDC} 2009, combined withe the 28th Chinese Control Conference, December
16-18, 2009, Shanghai, China},
pages = {3606--3613},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/CDC.2009.5400796},
doi = {10.1109/CDC.2009.5400796},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cdc/XuM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/XuCMY09,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor and
Sungho Yun},
title = {Risk sensitive robust support vector machines},
booktitle = {Proceedings of the 48th {IEEE} Conference on Decision and Control,
{CDC} 2009, combined withe the 28th Chinese Control Conference, December
16-18, 2009, Shanghai, China},
pages = {4655--4661},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/CDC.2009.5400598},
doi = {10.1109/CDC.2009.5400598},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/cdc/XuCMY09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/Even-DarKMM09,
author = {Eyal Even{-}Dar and
Robert Kleinberg and
Shie Mannor and
Yishay Mansour},
title = {Online Learning for Global Cost Functions},
booktitle = {{COLT} 2009 - The 22nd Conference on Learning Theory, Montreal, Quebec,
Canada, June 18-21, 2009},
year = {2009},
url = {http://www.cs.mcgill.ca/\%7Ecolt2009/papers/005.pdf\#page=1},
timestamp = {Thu, 04 Feb 2021 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/Even-DarKMM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gamenets/DanakM09,
author = {Amir Danak and
Shie Mannor},
editor = {Tamer Basar and
Hitay {\"{O}}zbay},
title = {Bidding efficiently in repeated auctions with entry and observation
costs},
booktitle = {1st International Conference on Game Theory for Networks, {GAMENETS}
2009, Istanbul, Turkey, May 13-15, 2009},
pages = {299--307},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/GAMENETS.2009.5137414},
doi = {10.1109/GAMENETS.2009.5137414},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/gamenets/DanakM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/gamenets/YuM09,
author = {Jia Yuan Yu and
Shie Mannor},
editor = {Tamer Basar and
Hitay {\"{O}}zbay},
title = {Online learning in Markov decision processes with arbitrarily changing
rewards and transitions},
booktitle = {1st International Conference on Game Theory for Networks, {GAMENETS}
2009, Istanbul, Turkey, May 13-15, 2009},
pages = {314--322},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/GAMENETS.2009.5137416},
doi = {10.1109/GAMENETS.2009.5137416},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/gamenets/YuM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/globecom/Leduc-PrimeauHGM09,
author = {Fran{\c{c}}ois Leduc{-}Primeau and
Saied Hemati and
Warren J. Gross and
Shie Mannor},
title = {A Relaxed Half-Stochastic Iterative Decoder for {LDPC} Codes},
booktitle = {Proceedings of the Global Communications Conference, 2009. {GLOBECOM}
2009, Honolulu, Hawaii, USA, 30 November - 4 December 2009},
pages = {1--6},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/GLOCOM.2009.5425510},
doi = {10.1109/GLOCOM.2009.5425510},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/globecom/Leduc-PrimeauHGM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icassp/TehraniNKMG09,
author = {Saeed Sharifi Tehrani and
Ali Naderi and
Guy{-}Armand Kamendje and
Shie Mannor and
Warren J. Gross},
title = {Tracking Forecast Memories in stochastic decoders},
booktitle = {Proceedings of the {IEEE} International Conference on Acoustics, Speech,
and Signal Processing, {ICASSP} 2009, 19-24 April 2009, Taipei, Taiwan},
pages = {561--564},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICASSP.2009.4959645},
doi = {10.1109/ICASSP.2009.4959645},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icassp/TehraniNKMG09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icc/SarkisMG09,
author = {Gabi Sarkis and
Shie Mannor and
Warren J. Gross},
title = {Stochastic Decoding of {LDPC} Codes over GF(q)},
booktitle = {Proceedings of {IEEE} International Conference on Communications,
{ICC} 2009, Dresden, Germany, 14-18 June 2009},
pages = {1--5},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ICC.2009.5199493},
doi = {10.1109/ICC.2009.5199493},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icc/SarkisMG09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/YuM09,
author = {Jia Yuan Yu and
Shie Mannor},
editor = {Andrea Pohoreckyj Danyluk and
L{\'{e}}on Bottou and
Michael L. Littman},
title = {Piecewise-stationary bandit problems with side observations},
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 = {1177--1184},
publisher = {{ACM}},
year = {2009},
url = {https://doi.org/10.1145/1553374.1553524},
doi = {10.1145/1553374.1553524},
timestamp = {Mon, 28 Aug 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/YuM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/itw/XuCM09,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
editor = {Bruce E. Hajek and
Leandros Tassiulas and
Venkat Anantharam and
Ioannis Kontoyiannis},
title = {High dimensional Principal Component Analysis with contaminated data},
booktitle = {2009 {IEEE} Information Theory Workshop, {ITW} 2009, Volos, Greece,
June 10-12, 2009},
pages = {246--250},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/ITWNIT.2009.5158580},
doi = {10.1109/ITWNIT.2009.5158580},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/itw/XuCM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sips/CushonGM09,
author = {Kevin Cushon and
Warren J. Gross and
Shie Mannor},
title = {Bidirectional interleavers for {LDPC} decoders using transmission
gates},
booktitle = {Proceedings of the {IEEE} Workshop on Signal Processing Systems, SiPS
2009, October 7-9, 2009, Tampere, Finland},
pages = {232--237},
publisher = {{IEEE}},
year = {2009},
url = {https://doi.org/10.1109/SIPS.2009.5336257},
doi = {10.1109/SIPS.2009.5336257},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sips/CushonGM09.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/geb/MannorS08,
author = {Shie Mannor and
Nahum Shimkin},
title = {Regret minimization in repeated matrix games with variable stage duration},
journal = {Games Econ. Behav.},
volume = {63},
number = {1},
pages = {227--258},
year = {2008},
url = {https://doi.org/10.1016/j.geb.2007.07.006},
doi = {10.1016/J.GEB.2007.07.006},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/geb/MannorS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/LugosiMS08,
author = {G{\'{a}}bor Lugosi and
Shie Mannor and
Gilles Stoltz},
title = {Strategies for Prediction Under Imperfect Monitoring},
journal = {Math. Oper. Res.},
volume = {33},
number = {3},
pages = {513--528},
year = {2008},
url = {https://doi.org/10.1287/moor.1080.0312},
doi = {10.1287/MOOR.1080.0312},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/LugosiMS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/TehraniMG08,
author = {Saeed Sharifi Tehrani and
Shie Mannor and
Warren J. Gross},
title = {Fully Parallel Stochastic {LDPC} Decoders},
journal = {{IEEE} Trans. Signal Process.},
volume = {56},
number = {11},
pages = {5692--5703},
year = {2008},
url = {https://doi.org/10.1109/TSP.2008.929671},
doi = {10.1109/TSP.2008.929671},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/TehraniMG08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KvetonYTM08,
author = {Branislav Kveton and
Jia Yuan Yu and
Georgios Theocharous and
Shie Mannor},
editor = {Dieter Fox and
Carla P. Gomes},
title = {Online Learning with Expert Advice and Finite-Horizon Constraints},
booktitle = {Proceedings of the Twenty-Third {AAAI} Conference on Artificial Intelligence,
{AAAI} 2008, Chicago, Illinois, USA, July 13-17, 2008},
pages = {331--336},
publisher = {{AAAI} Press},
year = {2008},
url = {http://www.aaai.org/Library/AAAI/2008/aaai08-052.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KvetonYTM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/ArcauteJM08,
author = {Esteban Arcaute and
Ramesh Johari and
Shie Mannor},
title = {Local dynamics for network formation games},
booktitle = {46th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2008, Monticello, IL, USA, September 24-26, 2008},
pages = {937--938},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ALLERTON.2008.4797658},
doi = {10.1109/ALLERTON.2008.4797658},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/ArcauteJM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/XuCM08,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Robust dimensionality reduction for high-dimension data},
booktitle = {46th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2008, Monticello, IL, USA, September 24-26, 2008},
pages = {1291--1298},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ALLERTON.2008.4797709},
doi = {10.1109/ALLERTON.2008.4797709},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/XuCM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/allerton/XuMC08,
author = {Huan Xu and
Shie Mannor and
Constantine Caramanis},
title = {Sparse algorithms are not stable: {A} no-free-lunch theorem},
booktitle = {46th Annual Allerton Conference on Communication, Control, and Computing,
Allerton 2008, Monticello, IL, USA, September 24-26, 2008},
pages = {1299--1303},
publisher = {{IEEE}},
year = {2008},
url = {https://doi.org/10.1109/ALLERTON.2008.4797710},
doi = {10.1109/ALLERTON.2008.4797710},
timestamp = {Sun, 17 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/allerton/XuMC08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/CaramanisM08,
author = {Constantine Caramanis and
Shie Mannor},
editor = {Rocco A. Servedio and
Tong Zhang},
title = {Learning in the Limit with Adversarial Disturbances},
booktitle = {21st Annual Conference on Learning Theory - {COLT} 2008, Helsinki,
Finland, July 9-12, 2008},
pages = {467--478},
publisher = {Omnipress},
year = {2008},
url = {http://colt2008.cs.helsinki.fi/papers/106-Caramanis.pdf},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/colt/CaramanisM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/DyagilevMS08,
author = {Kirill Dyagilev and
Shie Mannor and
Nahum Shimkin},
editor = {Sertan Girgin and
Manuel Loth and
R{\'{e}}mi Munos and
Philippe Preux and
Daniil Ryabko},
title = {Efficient Reinforcement Learning in Parameterized Models: Discrete
Parameter Case},
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 = {41--54},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-89722-4\_4},
doi = {10.1007/978-3-540-89722-4\_4},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/DyagilevMS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/FarahmandGSM08,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
editor = {Sertan Girgin and
Manuel Loth and
R{\'{e}}mi Munos and
Philippe Preux and
Daniil Ryabko},
title = {Regularized Fitted Q-Iteration: Application to Planning},
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 = {55--68},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-89722-4\_5},
doi = {10.1007/978-3-540-89722-4\_5},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/FarahmandGSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ewrl/YuMS08,
author = {Jia Yuan Yu and
Shie Mannor and
Nahum Shimkin},
editor = {Sertan Girgin and
Manuel Loth and
R{\'{e}}mi Munos and
Philippe Preux and
Daniil Ryabko},
title = {Markov Decision Processes with Arbitrary Reward Processes},
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 = {268--281},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-89722-4\_21},
doi = {10.1007/978-3-540-89722-4\_21},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ewrl/YuMS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/FrankMP08,
author = {Jordan Frank and
Shie Mannor and
Doina Precup},
editor = {William W. Cohen and
Andrew McCallum and
Sam T. Roweis},
title = {Reinforcement learning in the presence of rare events},
booktitle = {Machine Learning, Proceedings of the Twenty-Fifth International Conference
{(ICML} 2008), Helsinki, Finland, June 5-9, 2008},
series = {{ACM} International Conference Proceeding Series},
volume = {307},
pages = {336--343},
publisher = {{ACM}},
year = {2008},
url = {https://doi.org/10.1145/1390156.1390199},
doi = {10.1145/1390156.1390199},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/FrankMP08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/isaim/KvetonYTM08,
author = {Branislav Kveton and
Jia Yuan Yu and
Georgios Theocharous and
Shie Mannor},
title = {A Lazy Approach to Online Learning with Constraints},
booktitle = {International Symposium on Artificial Intelligence and Mathematics,
{ISAIM} 2008, Fort Lauderdale, Florida, USA, January 2-4, 2008},
year = {2008},
url = {http://isaim2008.unl.edu/PAPERS/TechnicalProgram/ISAIM2008\_0045\_f49e5d88c012a5932626e604063cbe90.pdf},
timestamp = {Thu, 12 Mar 2020 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/isaim/KvetonYTM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/FarahmandGSM08,
author = {Amir Massoud Farahmand and
Mohammad Ghavamzadeh and
Csaba Szepesv{\'{a}}ri and
Shie Mannor},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Regularized Policy Iteration},
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 = {441--448},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/aeb3135b436aa55373822c010763dd54-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/FarahmandGSM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuCM08,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
editor = {Daphne Koller and
Dale Schuurmans and
Yoshua Bengio and
L{\'{e}}on Bottou},
title = {Robust Regression and Lasso},
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 = {1801--1808},
publisher = {Curran Associates, Inc.},
year = {2008},
url = {https://proceedings.neurips.cc/paper/2008/hash/24681928425f5a9133504de568f5f6df-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/XuCM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/valuetools/DyagilevMS08,
author = {Kirill Dyagilev and
Shie Mannor and
Nahum Shimkin},
editor = {John S. Baras and
Costas Courcoubetis},
title = {Efficient reinforcement learning in parameterized models: discrete
parameters},
booktitle = {3rd International {ICST} Conference on Performance Evaluation Methodologies
and Tools, {VALUETOOLS} 2008, Athens, Greece, October 20-24, 2008},
pages = {64},
publisher = {{ICST/ACM}},
year = {2008},
url = {http://dl.acm.org/citation.cfm?id=1537038},
timestamp = {Tue, 24 Mar 2015 18:15:26 +0100},
biburl = {https://dblp.org/rec/conf/valuetools/DyagilevMS08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wine/ArcauteJM08,
author = {Esteban Arcaute and
Ramesh Johari and
Shie Mannor},
editor = {Christos H. Papadimitriou and
Shuzhong Zhang},
title = {Local Two-Stage Myopic Dynamics for Network Formation Games},
booktitle = {Internet and Network Economics, 4th International Workshop, {WINE}
2008, Shanghai, China, December 17-20, 2008. Proceedings},
series = {Lecture Notes in Computer Science},
volume = {5385},
pages = {263--277},
publisher = {Springer},
year = {2008},
url = {https://doi.org/10.1007/978-3-540-92185-1\_33},
doi = {10.1007/978-3-540-92185-1\_33},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/wine/ArcauteJM08.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-0803-3490,
author = {Huan Xu and
Shie Mannor and
Constantine Caramanis},
title = {Robustness, Risk, and Regularization in Support Vector Machines},
journal = {CoRR},
volume = {abs/0803.3490},
year = {2008},
url = {http://arxiv.org/abs/0803.3490},
eprinttype = {arXiv},
eprint = {0803.3490},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-0803-3490.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-0811-1790,
author = {Huan Xu and
Constantine Caramanis and
Shie Mannor},
title = {Robust Regression and Lasso},
journal = {CoRR},
volume = {abs/0811.1790},
year = {2008},
url = {http://arxiv.org/abs/0811.1790},
eprinttype = {arXiv},
eprint = {0811.1790},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-0811-1790.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ai/MannorS07,
author = {Shie Mannor and
Jeff S. Shamma},
title = {Multi-agent learning for engineers},
journal = {Artif. Intell.},
volume = {171},
number = {7},
pages = {417--422},
year = {2007},
url = {https://doi.org/10.1016/j.artint.2007.01.003},
doi = {10.1016/J.ARTINT.2007.01.003},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ai/MannorS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jsac/YuM07,
author = {Jia Yuan Yu and
Shie Mannor},
title = {Efficiency of Market-Based Resource Allocation among Many Participants},
journal = {{IEEE} J. Sel. Areas Commun.},
volume = {25},
number = {6},
pages = {1244--1259},
year = {2007},
url = {https://doi.org/10.1109/JSAC.2007.070818},
doi = {10.1109/JSAC.2007.070818},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jsac/YuM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mansci/MannorSST07,
author = {Shie Mannor and
Duncan Simester and
Peng Sun and
John N. Tsitsiklis},
title = {Bias and Variance Approximation in Value Function Estimates},
journal = {Manag. Sci.},
volume = {53},
number = {2},
pages = {308--322},
year = {2007},
url = {https://doi.org/10.1287/mnsc.1060.0614},
doi = {10.1287/MNSC.1060.0614},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mansci/MannorSST07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/MannorSA07,
author = {Shie Mannor and
Jeff S. Shamma and
G{\"{u}}rdal Arslan},
title = {Online calibrated forecasts: Memory efficiency versus universality
for learning in games},
journal = {Mach. Learn.},
volume = {67},
number = {1-2},
pages = {77--115},
year = {2007},
url = {https://doi.org/10.1007/s10994-006-0219-y},
doi = {10.1007/S10994-006-0219-Y},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/MannorSA07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tit/CaramanisM07,
author = {Constantine Caramanis and
Shie Mannor},
title = {An Inequality for Nearly Log-Concave Distributions With Applications
to Learning},
journal = {{IEEE} Trans. Inf. Theory},
volume = {53},
number = {3},
pages = {1043--1057},
year = {2007},
url = {https://doi.org/10.1109/TIT.2006.890699},
doi = {10.1109/TIT.2006.890699},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tit/CaramanisM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/KvetonGTMRS07,
author = {Branislav Kveton and
Prashant Gandhi and
Georgios Theocharous and
Shie Mannor and
Barbara Rosario and
Nilesh Shah},
title = {Adaptive Timeout Policies for Fast Fine-Grained Power Management},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {1795--1800},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-288.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/KvetonGTMRS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/aaai/YuMTP07,
author = {Chih{-}Han Yu and
Shie Mannor and
Georgios Theocharous and
Avi Pfeffer},
title = {User Model and Utility Based Power Management},
booktitle = {Proceedings of the Twenty-Second {AAAI} Conference on Artificial Intelligence,
July 22-26, 2007, Vancouver, British Columbia, Canada},
pages = {1918--1919},
publisher = {{AAAI} Press},
year = {2007},
url = {http://www.aaai.org/Library/AAAI/2007/aaai07-334.php},
timestamp = {Tue, 05 Sep 2023 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/aaai/YuMTP07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/ArcauteDJM07,
author = {Esteban Arcaute and
Eric Dallal and
Ramesh Johari and
Shie Mannor},
title = {Dynamics and stability in network formation games with bilateral contracts},
booktitle = {46th {IEEE} Conference on Decision and Control, {CDC} 2007, New Orleans,
LA, USA, December 12-14, 2007},
pages = {3435--3442},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/CDC.2007.4434965},
doi = {10.1109/CDC.2007.4434965},
timestamp = {Fri, 04 Mar 2022 13:27:03 +0100},
biburl = {https://dblp.org/rec/conf/cdc/ArcauteDJM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/LugosiMS07,
author = {G{\'{a}}bor Lugosi and
Shie Mannor and
Gilles Stoltz},
editor = {Nader H. Bshouty and
Claudio Gentile},
title = {Strategies for Prediction Under Imperfect Monitoring},
booktitle = {Learning Theory, 20th Annual Conference on Learning Theory, {COLT}
2007, San Diego, CA, USA, June 13-15, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4539},
pages = {248--262},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-72927-3\_19},
doi = {10.1007/978-3-540-72927-3\_19},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/LugosiMS07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/globecom/ChatelainMGP07,
author = {Beno{\^{\i}}t Ch{\^{a}}telain and
Shie Mannor and
Fran{\c{c}}ois Gagnon and
David V. Plant},
title = {Non-Cooperative Design of Translucent Networks},
booktitle = {Proceedings of the Global Communications Conference, 2007. {GLOBECOM}
'07, Washington, DC, USA, 26-30 November 2007},
pages = {2348--2352},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/GLOCOM.2007.447},
doi = {10.1109/GLOCOM.2007.447},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/globecom/ChatelainMGP07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/DelageM07,
author = {Erick Delage and
Shie Mannor},
editor = {Zoubin Ghahramani},
title = {Percentile optimization in uncertain Markov decision processes with
application to efficient exploration},
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 = {225--232},
publisher = {{ACM}},
year = {2007},
url = {https://doi.org/10.1145/1273496.1273525},
doi = {10.1145/1273496.1273525},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/DelageM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ismvl/TehraniMG07,
author = {Saeed Sharifi Tehrani and
Shie Mannor and
Warren J. Gross},
title = {Survey of Stochastic Computation on Factor Graphs},
booktitle = {37th International Symposium on Multiple-Valued Logic, {ISMVL} 2007,
13-16 May 2007, Oslo, Norway},
pages = {54},
publisher = {{IEEE} Computer Society},
year = {2007},
url = {https://doi.org/10.1109/ISMVL.2007.53},
doi = {10.1109/ISMVL.2007.53},
timestamp = {Thu, 23 Mar 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/ismvl/TehraniMG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/networking/HeidariMM07,
author = {Fariba Heidari and
Shie Mannor and
Lorne Mason},
editor = {Ian F. Akyildiz and
Raghupathy Sivakumar and
Eylem Ekici and
Jaudelice Cavalcante de Oliveira and
Janise McNair},
title = {Reinforcement Learning-Based Load Shared Sequential Routing},
booktitle = {{NETWORKING} 2007. Ad Hoc and Sensor Networks, Wireless Networks,
Next Generation Internet, 6th International {IFIP-TC6} Networking
Conference, Atlanta, GA, USA, May 14-18, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4479},
pages = {832--843},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-72606-7\_71},
doi = {10.1007/978-3-540-72606-7\_71},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/networking/HeidariMM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/sips/TehraniMG07,
author = {Saeed Sharifi Tehrani and
Shie Mannor and
Warren J. Gross},
title = {An Area-Efficient FPGA-Based Architecture for Fully-Parallel Stochastic
{LDPC} Decoding},
booktitle = {Proceedings of the {IEEE} Workshop on Signal Processing Systems, SiPS
2007, Proceedings, October 17-19, 2007, Eton Hotel, Shanghai, China},
pages = {255--260},
publisher = {{IEEE}},
year = {2007},
url = {https://doi.org/10.1109/SIPS.2007.4387554},
doi = {10.1109/SIPS.2007.4387554},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/sips/TehraniMG07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/wine/ArcauteJM07,
author = {Esteban Arcaute and
Ramesh Johari and
Shie Mannor},
editor = {Xiaotie Deng and
Fan Chung Graham},
title = {Network Formation: Bilateral Contracting and Myopic Dynamics},
booktitle = {Internet and Network Economics, Third International Workshop, {WINE}
2007, San Diego, CA, USA, December 12-14, 2007, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4858},
pages = {191--207},
publisher = {Springer},
year = {2007},
url = {https://doi.org/10.1007/978-3-540-77105-0\_20},
doi = {10.1007/978-3-540-77105-0\_20},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/wine/ArcauteJM07.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-math-0701419,
author = {G{\'{a}}bor Lugosi and
Shie Mannor and
Gilles Stoltz},
title = {Strategies for prediction under imperfect monitoring},
journal = {CoRR},
volume = {abs/math/0701419},
year = {2007},
url = {http://arxiv.org/abs/math/0701419},
eprinttype = {arXiv},
eprint = {math/0701419},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-math-0701419.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/geb/JohariMT06,
author = {Ramesh Johari and
Shie Mannor and
John N. Tsitsiklis},
title = {A contract-based model for directed network formation},
journal = {Games Econ. Behav.},
volume = {56},
number = {2},
pages = {201--224},
year = {2006},
url = {https://doi.org/10.1016/j.geb.2005.08.010},
doi = {10.1016/J.GEB.2005.08.010},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/geb/JohariMT06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/icl/TehraniGM06,
author = {Saeed Sharifi Tehrani and
Warren J. Gross and
Shie Mannor},
title = {Stochastic decoding of {LDPC} codes},
journal = {{IEEE} Commun. Lett.},
volume = {10},
number = {10},
pages = {716--718},
year = {2006},
url = {https://doi.org/10.1109/LCOMM.2006.060570},
doi = {10.1109/LCOMM.2006.060570},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/icl/TehraniGM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/Even-DarMM06,
author = {Eyal Even{-}Dar and
Shie Mannor and
Yishay Mansour},
title = {Action Elimination and Stopping Conditions for the Multi-Armed Bandit
and Reinforcement Learning Problems},
journal = {J. Mach. Learn. Res.},
volume = {7},
pages = {1079--1105},
year = {2006},
url = {http://jmlr.org/papers/v7/evendar06a.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/Even-DarMM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/CadotteMMB06,
author = {Patrick Cadotte and
Shie Mannor and
Hannah Michalska and
Benoit Boulet},
title = {Design of {\(\mathscr{l}\)}\({}_{\mbox{1}}\)-optimal controllers with
flexible disturbance rejection level},
journal = {{IEEE} Trans. Autom. Control.},
volume = {51},
number = {5},
pages = {868--873},
year = {2006},
url = {https://doi.org/10.1109/TAC.2006.875000},
doi = {10.1109/TAC.2006.875000},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/CadotteMMB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/amcc/CadotteMMB06,
author = {Patrick Cadotte and
Shie Mannor and
Hannah Michalska and
Benoit Boulet},
title = {Design of l1-Optimal Controllers with Flexible Disturbance Rejection
Level},
booktitle = {American Control Conference, {ACC} 2006, Minneapolis, MN, USA, 14-16
June, 2006},
pages = {1700--1705},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/ACC.2006.1656464},
doi = {10.1109/ACC.2006.1656464},
timestamp = {Tue, 27 Sep 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/amcc/CadotteMMB06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorS06,
author = {Shie Mannor and
Nahum Shimkin},
editor = {G{\'{a}}bor Lugosi and
Hans Ulrich Simon},
title = {Online Learning with Variable Stage Duration},
booktitle = {Learning Theory, 19th Annual Conference on Learning Theory, {COLT}
2006, Pittsburgh, PA, USA, June 22-25, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4005},
pages = {408--422},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11776420\_31},
doi = {10.1007/11776420\_31},
timestamp = {Fri, 08 Sep 2023 21:18:17 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorS06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorT06,
author = {Shie Mannor and
John N. Tsitsiklis},
editor = {G{\'{a}}bor Lugosi and
Hans Ulrich Simon},
title = {Online Learning with Constraints},
booktitle = {Learning Theory, 19th Annual Conference on Learning Theory, {COLT}
2006, Pittsburgh, PA, USA, June 22-25, 2006, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {4005},
pages = {529--543},
publisher = {Springer},
year = {2006},
url = {https://doi.org/10.1007/11776420\_39},
doi = {10.1007/11776420\_39},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorT06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/KellerMP06,
author = {Philipp W. Keller and
Shie Mannor and
Doina Precup},
editor = {William W. Cohen and
Andrew W. Moore},
title = {Automatic basis function construction for approximate dynamic programming
and reinforcement learning},
booktitle = {Machine Learning, Proceedings of the Twenty-Third International Conference
{(ICML} 2006), Pittsburgh, Pennsylvania, USA, June 25-29, 2006},
series = {{ACM} International Conference Proceeding Series},
volume = {148},
pages = {449--456},
publisher = {{ACM}},
year = {2006},
url = {https://doi.org/10.1145/1143844.1143901},
doi = {10.1145/1143844.1143901},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/KellerMP06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/infocom/YuM06,
author = {Jia Yuan Yu and
Shie Mannor},
title = {Asymptotics of Efficiency Loss in Competitive Market Mechanisms},
booktitle = {{INFOCOM} 2006. 25th {IEEE} International Conference on Computer Communications,
Joint Conference of the {IEEE} Computer and Communications Societies,
23-29 April 2006, Barcelona, Catalunya, Spain},
publisher = {{IEEE}},
year = {2006},
url = {https://doi.org/10.1109/INFOCOM.2006.255},
doi = {10.1109/INFOCOM.2006.255},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/infocom/YuM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/XuM06,
author = {Huan Xu and
Shie Mannor},
editor = {Bernhard Sch{\"{o}}lkopf and
John C. Platt and
Thomas Hofmann},
title = {The Robustness-Performance Tradeoff in Markov Decision Processes},
booktitle = {Advances in Neural Information Processing Systems 19, Proceedings
of the Twentieth Annual Conference on Neural Information Processing
Systems, Vancouver, British Columbia, Canada, December 4-7, 2006},
pages = {1537--1544},
publisher = {{MIT} Press},
year = {2006},
url = {https://proceedings.neurips.cc/paper/2006/hash/177540c7bcb8db31697b601642eac8d4-Abstract.html},
timestamp = {Tue, 12 Dec 2023 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/nips/XuM06.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/aim/MusleaDCJDCSFOCGBSJWSFMTPMABHGRG05,
author = {Ion Muslea and
Virginia Dignum and
Daniel D. Corkill and
Catholijn M. Jonker and
Frank Dignum and
Silvia Coradeschi and
Alessandro Saffiotti and
Dan Fu and
Jeff Orkin and
William Cheetham and
Kai Goebel and
Piero P. Bonissone and
Leen{-}Kiat Soh and
Randolph M. Jones and
Robert E. Wray III and
Matthias Scheutz and
Daniela Pucci de Farias and
Shie Mannor and
Georgios Theocharous and
Doina Precup and
Bamshad Mobasher and
Sarabjot S. Anand and
Bettina Berendt and
Andreas Hotho and
Hans W. Guesgen and
Michael T. Rosenstein and
Mohammad Ghavamzadeh},
title = {The Workshop Program at the Nineteenth National Conference on Artificial
Intelligence},
journal = {{AI} Mag.},
volume = {26},
number = {1},
pages = {103--108},
year = {2005},
url = {https://doi.org/10.1609/aimag.v26i1.1806},
doi = {10.1609/AIMAG.V26I1.1806},
timestamp = {Tue, 25 Aug 2020 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/aim/MusleaDCJDCSFOCGBSJWSFMTPMABHGRG05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/anor/BoerKMR05,
author = {Pieter{-}Tjerk de Boer and
Dirk P. Kroese and
Shie Mannor and
Reuven Y. Rubinstein},
title = {A Tutorial on the Cross-Entropy Method},
journal = {Ann. Oper. Res.},
volume = {134},
number = {1},
pages = {19--67},
year = {2005},
url = {https://doi.org/10.1007/s10479-005-5724-z},
doi = {10.1007/S10479-005-5724-Z},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/anor/BoerKMR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/anor/MenacheMS05,
author = {Ishai Menache and
Shie Mannor and
Nahum Shimkin},
title = {Basis Function Adaptation in Temporal Difference Reinforcement Learning},
journal = {Ann. Oper. Res.},
volume = {134},
number = {1},
pages = {215--238},
year = {2005},
url = {https://doi.org/10.1007/s10479-005-5732-z},
doi = {10.1007/S10479-005-5732-Z},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/anor/MenacheMS05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/MannorT05,
author = {Shie Mannor and
John N. Tsitsiklis},
title = {On the Empirical State-Action Frequencies in Markov Decision Processes
Under General Policies},
journal = {Math. Oper. Res.},
volume = {30},
number = {3},
pages = {545--561},
year = {2005},
url = {https://doi.org/10.1287/moor.1050.0148},
doi = {10.1287/MOOR.1050.0148},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/MannorT05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tac/JohariMT05,
author = {Ramesh Johari and
Shie Mannor and
John N. Tsitsiklis},
title = {Efficiency loss in a network resource allocation game: the case of
elastic supply},
journal = {{IEEE} Trans. Autom. Control.},
volume = {50},
number = {11},
pages = {1712--1724},
year = {2005},
url = {https://doi.org/10.1109/TAC.2005.858687},
doi = {10.1109/TAC.2005.858687},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tac/JohariMT05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/EngelMM05,
author = {Yaakov Engel and
Shie Mannor and
Ron Meir},
editor = {Luc De Raedt and
Stefan Wrobel},
title = {Reinforcement learning with Gaussian processes},
booktitle = {Machine Learning, Proceedings of the Twenty-Second International Conference
{(ICML} 2005), Bonn, Germany, August 7-11, 2005},
series = {{ACM} International Conference Proceeding Series},
volume = {119},
pages = {201--208},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1102351.1102377},
doi = {10.1145/1102351.1102377},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/EngelMM05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorPR05,
author = {Shie Mannor and
Dori Peleg and
Reuven Y. Rubinstein},
editor = {Luc De Raedt and
Stefan Wrobel},
title = {The cross entropy method for classification},
booktitle = {Machine Learning, Proceedings of the Twenty-Second International Conference
{(ICML} 2005), Bonn, Germany, August 7-11, 2005},
series = {{ACM} International Conference Proceeding Series},
volume = {119},
pages = {561--568},
publisher = {{ACM}},
year = {2005},
url = {https://doi.org/10.1145/1102351.1102422},
doi = {10.1145/1102351.1102422},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/icml/MannorPR05.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-cs-0506054,
author = {Ramesh Johari and
Shie Mannor and
John N. Tsitsiklis},
title = {Efficiency Loss in a Network Resource Allocation Game: The Case of
Elastic Supply},
journal = {CoRR},
volume = {abs/cs/0506054},
year = {2005},
url = {http://arxiv.org/abs/cs/0506054},
eprinttype = {arXiv},
eprint = {cs/0506054},
timestamp = {Mon, 13 Aug 2018 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-cs-0506054.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MannorS04,
author = {Shie Mannor and
Nahum Shimkin},
title = {A Geometric Approach to Multi-Criterion Reinforcement Learning},
journal = {J. Mach. Learn. Res.},
volume = {5},
pages = {325--360},
year = {2004},
url = {http://jmlr.org/papers/volume5/mannor04a/mannor04a.pdf},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorS04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MannorT04,
author = {Shie Mannor and
John N. Tsitsiklis},
title = {The Sample Complexity of Exploration in the Multi-Armed Bandit Problem},
journal = {J. Mach. Learn. Res.},
volume = {5},
pages = {623--648},
year = {2004},
url = {http://jmlr.org/papers/volume5/mannor04b/mannor04b.pdf},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorT04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tsp/EngelMM04,
author = {Yaakov Engel and
Shie Mannor and
Ron Meir},
title = {The kernel recursive least-squares algorithm},
journal = {{IEEE} Trans. Signal Process.},
volume = {52},
number = {8},
pages = {2275--2285},
year = {2004},
url = {https://doi.org/10.1109/TSP.2004.830985},
doi = {10.1109/TSP.2004.830985},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/tsp/EngelMM04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/cdc/JohariMT04,
author = {Ramesh Johari and
Shie Mannor and
John N. Tsitsiklis},
title = {Efficiency loss in a resource allocation game: {A} single link in
elastic supply},
booktitle = {43rd {IEEE} Conference on Decision and Control, {CDC} 2004, Nassau,
Bahamas, December 14-17, 2004},
pages = {4679--4683},
publisher = {{IEEE}},
year = {2004},
url = {https://doi.org/10.1109/CDC.2004.1429527},
doi = {10.1109/CDC.2004.1429527},
timestamp = {Sat, 09 Apr 2022 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/cdc/JohariMT04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/Mannor04,
author = {Shie Mannor},
editor = {John Shawe{-}Taylor and
Yoram Singer},
title = {Reinforcement Learning for Average Reward Zero-Sum Games},
booktitle = {Learning Theory, 17th Annual Conference on Learning Theory, {COLT}
2004, Banff, Canada, July 1-4, 2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3120},
pages = {49--63},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-27819-1\_4},
doi = {10.1007/978-3-540-27819-1\_4},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/Mannor04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/CaramanisM04,
author = {Constantine Caramanis and
Shie Mannor},
editor = {John Shawe{-}Taylor and
Yoram Singer},
title = {An Inequality for Nearly Log-Concave Distributions with Applications
to Learning},
booktitle = {Learning Theory, 17th Annual Conference on Learning Theory, {COLT}
2004, Banff, Canada, July 1-4, 2004, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {3120},
pages = {534--548},
publisher = {Springer},
year = {2004},
url = {https://doi.org/10.1007/978-3-540-27819-1\_37},
doi = {10.1007/978-3-540-27819-1\_37},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/CaramanisM04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorMHK04,
author = {Shie Mannor and
Ishai Menache and
Amit Hoze and
Uri Klein},
editor = {Carla E. Brodley},
title = {Dynamic abstraction in reinforcement learning via clustering},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
series = {{ACM} International Conference Proceeding Series},
volume = {69},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1015330.1015355},
doi = {10.1145/1015330.1015355},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MannorMHK04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorSST04,
author = {Shie Mannor and
Duncan Simester and
Peng Sun and
John N. Tsitsiklis},
editor = {Carla E. Brodley},
title = {Bias and variance in value function estimation},
booktitle = {Machine Learning, Proceedings of the Twenty-first International Conference
{(ICML} 2004), Banff, Alberta, Canada, July 4-8, 2004},
series = {{ACM} International Conference Proceeding Series},
volume = {69},
publisher = {{ACM}},
year = {2004},
url = {https://doi.org/10.1145/1015330.1015402},
doi = {10.1145/1015330.1015402},
timestamp = {Tue, 06 Nov 2018 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MannorSST04.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/jmlr/MannorMZ03,
author = {Shie Mannor and
Ron Meir and
Tong Zhang},
title = {Greedy Algorithms for Classification -- Consistency, Convergence Rates,
and Adaptivity},
journal = {J. Mach. Learn. Res.},
volume = {4},
pages = {713--741},
year = {2003},
url = {http://jmlr.org/papers/v4/mannor03a.html},
timestamp = {Wed, 10 Jul 2019 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/jmlr/MannorMZ03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/mor/MannorS03,
author = {Shie Mannor and
Nahum Shimkin},
title = {The Empirical Bayes Envelope and Regret Minimization in Competitive
Markov Decision Processes},
journal = {Math. Oper. Res.},
volume = {28},
number = {2},
pages = {327--345},
year = {2003},
url = {https://doi.org/10.1287/moor.28.2.327.14483},
doi = {10.1287/MOOR.28.2.327.14483},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/mor/MannorS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorT03,
author = {Shie Mannor and
John N. Tsitsiklis},
editor = {Bernhard Sch{\"{o}}lkopf and
Manfred K. Warmuth},
title = {Lower Bounds on the Sample Complexity of Exploration in the Multi-armed
Bandit Problem},
booktitle = {Computational Learning Theory and Kernel Machines, 16th Annual Conference
on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel
2003, Washington, DC, USA, August 24-27, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2777},
pages = {418--432},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-45167-9\_31},
doi = {10.1007/978-3-540-45167-9\_31},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorT03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorS03,
author = {Shie Mannor and
Nahum Shimkin},
editor = {Bernhard Sch{\"{o}}lkopf and
Manfred K. Warmuth},
title = {On-Line Learning with Imperfect Monitoring},
booktitle = {Computational Learning Theory and Kernel Machines, 16th Annual Conference
on Computational Learning Theory and 7th Kernel Workshop, COLT/Kernel
2003, Washington, DC, USA, August 24-27, 2003, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2777},
pages = {552--566},
publisher = {Springer},
year = {2003},
url = {https://doi.org/10.1007/978-3-540-45167-9\_40},
doi = {10.1007/978-3-540-45167-9\_40},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorS03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/EngelMM03,
author = {Yaakov Engel and
Shie Mannor and
Ron Meir},
editor = {Tom Fawcett and
Nina Mishra},
title = {Bayes Meets Bellman: The Gaussian Process Approach to Temporal Difference
Learning},
booktitle = {Machine Learning, Proceedings of the Twentieth International Conference
{(ICML} 2003), August 21-24, 2003, Washington, DC, {USA}},
pages = {154--161},
publisher = {{AAAI} Press},
year = {2003},
url = {http://www.aaai.org/Library/ICML/2003/icml03-023.php},
timestamp = {Thu, 13 Dec 2012 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/EngelMM03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/Even-DarMM03,
author = {Eyal Even{-}Dar and
Shie Mannor and
Yishay Mansour},
editor = {Tom Fawcett and
Nina Mishra},
title = {Action Elimination and Stopping Conditions for Reinforcement Learning},
booktitle = {Machine Learning, Proceedings of the Twentieth International Conference
{(ICML} 2003), August 21-24, 2003, Washington, DC, {USA}},
pages = {162--169},
publisher = {{AAAI} Press},
year = {2003},
url = {http://www.aaai.org/Library/ICML/2003/icml03-024.php},
timestamp = {Thu, 13 Dec 2012 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/Even-DarMM03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/MannorRG03,
author = {Shie Mannor and
Reuven Y. Rubinstein and
Yohai Gat},
editor = {Tom Fawcett and
Nina Mishra},
title = {The Cross Entropy Method for Fast Policy Search},
booktitle = {Machine Learning, Proceedings of the Twentieth International Conference
{(ICML} 2003), August 21-24, 2003, Washington, DC, {USA}},
pages = {512--519},
publisher = {{AAAI} Press},
year = {2003},
url = {http://www.aaai.org/Library/ICML/2003/icml03-068.php},
timestamp = {Thu, 13 Dec 2012 00:00:00 +0100},
biburl = {https://dblp.org/rec/conf/icml/MannorRG03.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/ml/MannorM02,
author = {Shie Mannor and
Ron Meir},
title = {On the Existence of Linear Weak Learners and Applications to Boosting},
journal = {Mach. Learn.},
volume = {48},
number = {1-3},
pages = {219--251},
year = {2002},
url = {https://doi.org/10.1023/A:1013959922467},
doi = {10.1023/A:1013959922467},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/journals/ml/MannorM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/Even-DarMM02,
author = {Eyal Even{-}Dar and
Shie Mannor and
Yishay Mansour},
editor = {Jyrki Kivinen and
Robert H. Sloan},
title = {{PAC} Bounds for Multi-armed Bandit and Markov Decision Processes},
booktitle = {Computational Learning Theory, 15th Annual Conference on Computational
Learning Theory, {COLT} 2002, Sydney, Australia, July 8-10, 2002,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2375},
pages = {255--270},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-45435-7\_18},
doi = {10.1007/3-540-45435-7\_18},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/Even-DarMM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorMZ02,
author = {Shie Mannor and
Ron Meir and
Tong Zhang},
editor = {Jyrki Kivinen and
Robert H. Sloan},
title = {The Consistency of Greedy Algorithms for Classification},
booktitle = {Computational Learning Theory, 15th Annual Conference on Computational
Learning Theory, {COLT} 2002, Sydney, Australia, July 8-10, 2002,
Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2375},
pages = {319--333},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-45435-7\_22},
doi = {10.1007/3-540-45435-7\_22},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorMZ02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/EngelMM02,
author = {Yaakov Engel and
Shie Mannor and
Ron Meir},
editor = {Tapio Elomaa and
Heikki Mannila and
Hannu Toivonen},
title = {Sparse Online Greedy Support Vector Regression},
booktitle = {Machine Learning: {ECML} 2002, 13th European Conference on Machine
Learning, Helsinki, Finland, August 19-23, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2430},
pages = {84--96},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-36755-1\_8},
doi = {10.1007/3-540-36755-1\_8},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecml/EngelMM02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/ecml/MenacheMS02,
author = {Ishai Menache and
Shie Mannor and
Nahum Shimkin},
editor = {Tapio Elomaa and
Heikki Mannila and
Hannu Toivonen},
title = {Q-Cut - Dynamic Discovery of Sub-goals in Reinforcement Learning},
booktitle = {Machine Learning: {ECML} 2002, 13th European Conference on Machine
Learning, Helsinki, Finland, August 19-23, 2002, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2430},
pages = {295--306},
publisher = {Springer},
year = {2002},
url = {https://doi.org/10.1007/3-540-36755-1\_25},
doi = {10.1007/3-540-36755-1\_25},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/ecml/MenacheMS02.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorS01,
author = {Shie Mannor and
Nahum Shimkin},
editor = {David P. Helmbold and
Robert C. Williamson},
title = {Adaptive Strategies and Regret Minimization in Arbitrarily Varying
Markov Environments},
booktitle = {Computational Learning Theory, 14th Annual Conference on Computational
Learning Theory, {COLT} 2001 and 5th European Conference on Computational
Learning Theory, EuroCOLT 2001, Amsterdam, The Netherlands, July 16-19,
2001, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2111},
pages = {128--142},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-44581-1\_9},
doi = {10.1007/3-540-44581-1\_9},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/colt/MannorM01,
author = {Shie Mannor and
Ron Meir},
editor = {David P. Helmbold and
Robert C. Williamson},
title = {Geometric Bounds for Generalization in Boosting},
booktitle = {Computational Learning Theory, 14th Annual Conference on Computational
Learning Theory, {COLT} 2001 and 5th European Conference on Computational
Learning Theory, EuroCOLT 2001, Amsterdam, The Netherlands, July 16-19,
2001, Proceedings},
series = {Lecture Notes in Computer Science},
volume = {2111},
pages = {461--472},
publisher = {Springer},
year = {2001},
url = {https://doi.org/10.1007/3-540-44581-1\_30},
doi = {10.1007/3-540-44581-1\_30},
timestamp = {Thu, 14 Oct 2021 01:00:00 +0200},
biburl = {https://dblp.org/rec/conf/colt/MannorM01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/EngelM01,
author = {Yaakov Engel and
Shie Mannor},
editor = {Carla E. Brodley and
Andrea Pohoreckyj Danyluk},
title = {Learning Embedded Maps of Markov Processes},
booktitle = {Proceedings of the Eighteenth International Conference on Machine
Learning {(ICML} 2001), Williams College, Williamstown, MA, USA, June
28 - July 1, 2001},
pages = {138--145},
publisher = {Morgan Kaufmann},
year = {2001},
timestamp = {Wed, 27 Nov 2002 10:53:35 +0100},
biburl = {https://dblp.org/rec/conf/icml/EngelM01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MannorS01,
author = {Shie Mannor and
Nahum Shimkin},
editor = {Thomas G. Dietterich and
Suzanna Becker and
Zoubin Ghahramani},
title = {The Steering Approach for Multi-Criteria Reinforcement Learning},
booktitle = {Advances in Neural Information Processing Systems 14 [Neural Information
Processing Systems: Natural and Synthetic, {NIPS} 2001, December 3-8,
2001, Vancouver, British Columbia, Canada]},
pages = {1563--1570},
publisher = {{MIT} Press},
year = {2001},
url = {https://proceedings.neurips.cc/paper/2001/hash/8c249675aea6c3cbd91661bbae767ff1-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MannorS01.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/MannorM00,
author = {Shie Mannor and
Ron Meir},
editor = {Todd K. Leen and
Thomas G. Dietterich and
Volker Tresp},
title = {Weak Learners and Improved Rates of Convergence in Boosting},
booktitle = {Advances in Neural Information Processing Systems 13, Papers from
Neural Information Processing Systems {(NIPS)} 2000, Denver, CO, {USA}},
pages = {280--286},
publisher = {{MIT} Press},
year = {2000},
url = {https://proceedings.neurips.cc/paper/2000/hash/dea9ddb25cbf2352cf4dec30222a02a5-Abstract.html},
timestamp = {Mon, 16 May 2022 15:41:51 +0200},
biburl = {https://dblp.org/rec/conf/nips/MannorM00.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
a service of 
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.
last updated on 2024-04-25 05:44 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
