Search dblp for Publications

export results for "author:Lingxiao_Wang_0003:"

 download as .bib file

@article{DBLP:journals/ai/BaiWHYZWL24,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Jianye Hao and
                  Zhuoran Yang and
                  Bin Zhao and
                  Zhen Wang and
                  Xuelong Li},
  title        = {Pessimistic value iteration for multi-task data sharing in Offline
                  Reinforcement Learning},
  journal      = {Artif. Intell.},
  volume       = {326},
  pages        = {104048},
  year         = {2024},
  url          = {https://doi.org/10.1016/j.artint.2023.104048},
  doi          = {10.1016/J.ARTINT.2023.104048},
  timestamp    = {Tue, 26 Mar 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/ai/BaiWHYZWL24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/pami/DengFWYBZWJ24,
  author       = {Zhihong Deng and
                  Zuyue Fu and
                  Lingxiao Wang and
                  Zhuoran Yang and
                  Chenjia Bai and
                  Tianyi Zhou and
                  Zhaoran Wang and
                  Jing Jiang},
  title        = {False Correlation Reduction for Offline Reinforcement Learning},
  journal      = {{IEEE} Trans. Pattern Anal. Mach. Intell.},
  volume       = {46},
  number       = {2},
  pages        = {1199--1211},
  year         = {2024},
  url          = {https://doi.org/10.1109/TPAMI.2023.3328397},
  doi          = {10.1109/TPAMI.2023.3328397},
  timestamp    = {Fri, 26 Jan 2024 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/pami/DengFWYBZWJ24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tnn/BaiXZWZGHLW24,
  author       = {Chenjia Bai and
                  Ting Xiao and
                  Zhoufan Zhu and
                  Lingxiao Wang and
                  Fan Zhou and
                  Animesh Garg and
                  Bin He and
                  Peng Liu and
                  Zhaoran Wang},
  title        = {Monotonic Quantile Network for Worst-Case Offline Reinforcement Learning},
  journal      = {{IEEE} Trans. Neural Networks Learn. Syst.},
  volume       = {35},
  number       = {7},
  pages        = {8954--8968},
  year         = {2024},
  url          = {https://doi.org/10.1109/TNNLS.2022.3217189},
  doi          = {10.1109/TNNLS.2022.3217189},
  timestamp    = {Fri, 02 Aug 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/tnn/BaiXZWZGHLW24.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2404-19346,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Jianye Hao and
                  Zhuoran Yang and
                  Bin Zhao and
                  Zhen Wang and
                  Xuelong Li},
  title        = {Pessimistic Value Iteration for Multi-Task Data Sharing in Offline
                  Reinforcement Learning},
  journal      = {CoRR},
  volume       = {abs/2404.19346},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2404.19346},
  doi          = {10.48550/ARXIV.2404.19346},
  eprinttype    = {arXiv},
  eprint       = {2404.19346},
  timestamp    = {Mon, 22 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2404-19346.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tcyb/BaiWWWZBL23,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Yixin Wang and
                  Zhaoran Wang and
                  Rui Zhao and
                  Chenyao Bai and
                  Peng Liu},
  title        = {Addressing Hindsight Bias in Multigoal Reinforcement Learning},
  journal      = {{IEEE} Trans. Cybern.},
  volume       = {53},
  number       = {1},
  pages        = {392--405},
  year         = {2023},
  url          = {https://doi.org/10.1109/TCYB.2021.3107202},
  doi          = {10.1109/TCYB.2021.3107202},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tcyb/BaiWWWZBL23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/tnn/BaiLLWZHW23,
  author       = {Chenjia Bai and
                  Peng Liu and
                  Kaiyu Liu and
                  Lingxiao Wang and
                  Yingnan Zhao and
                  Lei Han and
                  Zhaoran Wang},
  title        = {Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement
                  Learning},
  journal      = {{IEEE} Trans. Neural Networks Learn. Syst.},
  volume       = {34},
  number       = {8},
  pages        = {4776--4790},
  year         = {2023},
  url          = {https://doi.org/10.1109/TNNLS.2021.3129160},
  doi          = {10.1109/TNNLS.2021.3129160},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/tnn/BaiLLWZHW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/0003CYW23,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Represent to Control Partially Observed Systems: Representation Learning
                  with Provable Sample Efficiency},
  booktitle    = {The Eleventh International Conference on Learning Representations,
                  {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
  publisher    = {OpenReview.net},
  year         = {2023},
  url          = {https://openreview.net/forum?id=8oJHwb3Sgp},
  timestamp    = {Wed, 24 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/0003CYW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Zheng0QFYSW23,
  author       = {Sirui Zheng and
                  Lingxiao Wang and
                  Shuang Qiu and
                  Zuyue Fu and
                  Zhuoran Yang and
                  Csaba Szepesv{\'{a}}ri and
                  Zhaoran Wang},
  title        = {Optimistic Exploration with Learned Features Provably Solves Markov
                  Decision Processes with Neural Dynamics},
  booktitle    = {The Eleventh International Conference on Learning Representations,
                  {ICLR} 2023, Kigali, Rwanda, May 1-5, 2023},
  publisher    = {OpenReview.net},
  year         = {2023},
  url          = {https://openreview.net/forum?id=9kBCMNb5mc},
  timestamp    = {Wed, 24 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/conf/iclr/Zheng0QFYSW23.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2305-18464,
  author       = {Haoran He and
                  Chenjia Bai and
                  Hang Lai and
                  Lingxiao Wang and
                  Weinan Zhang},
  title        = {Privileged Knowledge Distillation for Sim-to-Real Policy Generalization},
  journal      = {CoRR},
  volume       = {abs/2305.18464},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2305.18464},
  doi          = {10.48550/ARXIV.2305.18464},
  eprinttype    = {arXiv},
  eprint       = {2305.18464},
  timestamp    = {Fri, 09 Jun 2023 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2305-18464.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/Bai0YDG0W22,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Zhuoran Yang and
                  Zhi{-}Hong Deng and
                  Animesh Garg and
                  Peng Liu and
                  Zhaoran Wang},
  title        = {Pessimistic Bootstrapping for Uncertainty-Driven Offline 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=Y4cs1Z3HnqL},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iclr/Bai0YDG0W22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/QiuWBYW22,
  author       = {Shuang Qiu and
                  Lingxiao Wang and
                  Chenjia Bai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  editor       = {Kamalika Chaudhuri and
                  Stefanie Jegelka and
                  Le Song and
                  Csaba Szepesv{\'{a}}ri and
                  Gang Niu and
                  Sivan Sabato},
  title        = {Contrastive {UCB:} Provably Efficient Contrastive Self-Supervised
                  Learning in Online 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        = {18168--18210},
  publisher    = {{PMLR}},
  year         = {2022},
  url          = {https://proceedings.mlr.press/v162/qiu22c.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icml/QiuWBYW22.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2202-11566,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Zhuoran Yang and
                  Zhihong Deng and
                  Animesh Garg and
                  Peng Liu and
                  Zhaoran Wang},
  title        = {Pessimistic Bootstrapping for Uncertainty-Driven Offline Reinforcement
                  Learning},
  journal      = {CoRR},
  volume       = {abs/2202.11566},
  year         = {2022},
  url          = {https://arxiv.org/abs/2202.11566},
  eprinttype    = {arXiv},
  eprint       = {2202.11566},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2202-11566.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2205-13476,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Embed to Control Partially Observed Systems: Representation Learning
                  with Provable Sample Efficiency},
  journal      = {CoRR},
  volume       = {abs/2205.13476},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2205.13476},
  doi          = {10.48550/ARXIV.2205.13476},
  eprinttype    = {arXiv},
  eprint       = {2205.13476},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2205-13476.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2207-14800,
  author       = {Shuang Qiu and
                  Lingxiao Wang and
                  Chenjia Bai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Contrastive {UCB:} Provably Efficient Contrastive Self-Supervised
                  Learning in Online Reinforcement Learning},
  journal      = {CoRR},
  volume       = {abs/2207.14800},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2207.14800},
  doi          = {10.48550/ARXIV.2207.14800},
  eprinttype    = {arXiv},
  eprint       = {2207.14800},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2207-14800.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2212-14852,
  author       = {Yufeng Zhang and
                  Boyi Liu and
                  Qi Cai and
                  Lingxiao Wang and
                  Zhaoran Wang},
  title        = {An Analysis of Attention via the Lens of Exchangeability and Latent
                  Variable Models},
  journal      = {CoRR},
  volume       = {abs/2212.14852},
  year         = {2022},
  url          = {https://doi.org/10.48550/arXiv.2212.14852},
  doi          = {10.48550/ARXIV.2212.14852},
  eprinttype    = {arXiv},
  eprint       = {2212.14852},
  timestamp    = {Fri, 19 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2212-14852.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/BaiWHHG0W21,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Lei Han and
                  Jianye Hao and
                  Animesh Garg and
                  Peng Liu and
                  Zhaoran Wang},
  editor       = {Marina Meila and
                  Tong Zhang},
  title        = {Principled Exploration via Optimistic Bootstrapping and Backward Induction},
  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        = {577--587},
  publisher    = {{PMLR}},
  year         = {2021},
  url          = {http://proceedings.mlr.press/v139/bai21d.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icml/BaiWHHG0W21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/BaiWHGHLW21,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Lei Han and
                  Animesh Garg and
                  Jianye Hao and
                  Peng Liu and
                  Zhaoran Wang},
  editor       = {Marc'Aurelio Ranzato and
                  Alina Beygelzimer and
                  Yann N. Dauphin and
                  Percy Liang and
                  Jennifer Wortman Vaughan},
  title        = {Dynamic Bottleneck for Robust Self-Supervised Exploration},
  booktitle    = {Advances in Neural Information Processing Systems 34: Annual Conference
                  on Neural Information Processing Systems 2021, NeurIPS 2021, December
                  6-14, 2021, virtual},
  pages        = {17007--17020},
  year         = {2021},
  url          = {https://proceedings.neurips.cc/paper/2021/hash/8d3369c4c086f236fabf61d614a32818-Abstract.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/BaiWHGHLW21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WangYW21,
  author       = {Lingxiao Wang and
                  Zhuoran Yang and
                  Zhaoran Wang},
  editor       = {Marc'Aurelio Ranzato and
                  Alina Beygelzimer and
                  Yann N. Dauphin and
                  Percy Liang and
                  Jennifer Wortman Vaughan},
  title        = {Provably Efficient Causal Reinforcement Learning with Confounded Observational
                  Data},
  booktitle    = {Advances in Neural Information Processing Systems 34: Annual Conference
                  on Neural Information Processing Systems 2021, NeurIPS 2021, December
                  6-14, 2021, virtual},
  pages        = {21164--21175},
  year         = {2021},
  url          = {https://proceedings.neurips.cc/paper/2021/hash/b0b79da57b95837f14be95aaa4d54cf8-Abstract.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/WangYW21.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-06022,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Lei Han and
                  Jianye Hao and
                  Animesh Garg and
                  Peng Liu and
                  Zhaoran Wang},
  title        = {Principled Exploration via Optimistic Bootstrapping and Backward Induction},
  journal      = {CoRR},
  volume       = {abs/2105.06022},
  year         = {2021},
  url          = {https://arxiv.org/abs/2105.06022},
  eprinttype    = {arXiv},
  eprint       = {2105.06022},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2105-06022.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2105-08268,
  author       = {Yan Li and
                  Lingxiao Wang and
                  Jiachen Yang and
                  Ethan Wang and
                  Zhaoran Wang and
                  Tuo Zhao and
                  Hongyuan Zha},
  title        = {Permutation Invariant Policy Optimization for Mean-Field Multi-Agent
                  Reinforcement Learning: {A} Principled Approach},
  journal      = {CoRR},
  volume       = {abs/2105.08268},
  year         = {2021},
  url          = {https://arxiv.org/abs/2105.08268},
  eprinttype    = {arXiv},
  eprint       = {2105.08268},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2105-08268.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-10735,
  author       = {Chenjia Bai and
                  Lingxiao Wang and
                  Lei Han and
                  Animesh Garg and
                  Jianye Hao and
                  Peng Liu and
                  Zhaoran Wang},
  title        = {Dynamic Bottleneck for Robust Self-Supervised Exploration},
  journal      = {CoRR},
  volume       = {abs/2110.10735},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.10735},
  eprinttype    = {arXiv},
  eprint       = {2110.10735},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-10735.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2110-12468,
  author       = {Zhihong Deng and
                  Zuyue Fu and
                  Lingxiao Wang and
                  Zhuoran Yang and
                  Chenjia Bai and
                  Zhaoran Wang and
                  Jing Jiang},
  title        = {{SCORE:} Spurious COrrelation REduction for Offline Reinforcement
                  Learning},
  journal      = {CoRR},
  volume       = {abs/2110.12468},
  year         = {2021},
  url          = {https://arxiv.org/abs/2110.12468},
  eprinttype    = {arXiv},
  eprint       = {2110.12468},
  timestamp    = {Mon, 22 Jul 2024 01:00:00 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2110-12468.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/iclr/WangCYW20,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Neural Policy Gradient Methods: Global Optimality and Rates of Convergence},
  booktitle    = {8th International Conference on Learning Representations, {ICLR} 2020,
                  Addis Ababa, Ethiopia, April 26-30, 2020},
  publisher    = {OpenReview.net},
  year         = {2020},
  url          = {https://openreview.net/forum?id=BJgQfkSYDS},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/iclr/WangCYW20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangCYW20,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {On the Global Optimality of Model-Agnostic Meta-Learning},
  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        = {9837--9846},
  publisher    = {{PMLR}},
  year         = {2020},
  url          = {http://proceedings.mlr.press/v119/wang20b.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icml/WangCYW20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/icml/WangYW20,
  author       = {Lingxiao Wang and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration
                  for Mean-Field Reinforcement Learning},
  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        = {10092--10103},
  publisher    = {{PMLR}},
  year         = {2020},
  url          = {http://proceedings.mlr.press/v119/wang20z.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/icml/WangYW20.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-11917,
  author       = {Lingxiao Wang and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Breaking the Curse of Many Agents: Provable Mean Embedding Q-Iteration
                  for Mean-Field Reinforcement Learning},
  journal      = {CoRR},
  volume       = {abs/2006.11917},
  year         = {2020},
  url          = {https://arxiv.org/abs/2006.11917},
  eprinttype    = {arXiv},
  eprint       = {2006.11917},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2006-11917.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-12311,
  author       = {Lingxiao Wang and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Provably Efficient Causal Reinforcement Learning with Confounded Observational
                  Data},
  journal      = {CoRR},
  volume       = {abs/2006.12311},
  year         = {2020},
  url          = {https://arxiv.org/abs/2006.12311},
  eprinttype    = {arXiv},
  eprint       = {2006.12311},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2006-12311.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2006-13182,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {On the Global Optimality of Model-Agnostic Meta-Learning},
  journal      = {CoRR},
  volume       = {abs/2006.13182},
  year         = {2020},
  url          = {https://arxiv.org/abs/2006.13182},
  eprinttype    = {arXiv},
  eprint       = {2006.13182},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2006-13182.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-2010-08755,
  author       = {Chenjia Bai and
                  Peng Liu and
                  Zhaoran Wang and
                  Kaiyu Liu and
                  Lingxiao Wang and
                  Yingnan Zhao},
  title        = {Variational Dynamic for Self-Supervised Exploration in Deep Reinforcement
                  Learning},
  journal      = {CoRR},
  volume       = {abs/2010.08755},
  year         = {2020},
  url          = {https://arxiv.org/abs/2010.08755},
  eprinttype    = {arXiv},
  eprint       = {2010.08755},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2010-08755.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@inproceedings{DBLP:conf/nips/WangYW19,
  author       = {Lingxiao Wang and
                  Zhuoran Yang and
                  Zhaoran Wang},
  editor       = {Hanna M. Wallach and
                  Hugo Larochelle and
                  Alina Beygelzimer and
                  Florence d'Alch{\'{e}}{-}Buc and
                  Emily B. Fox and
                  Roman Garnett},
  title        = {Statistical-Computational Tradeoff in Single Index Models},
  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        = {10419--10426},
  year         = {2019},
  url          = {https://proceedings.neurips.cc/paper/2019/hash/13d4635deccc230c944e4ff6e03404b5-Abstract.html},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/conf/nips/WangYW19.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
@article{DBLP:journals/corr/abs-1909-01150,
  author       = {Lingxiao Wang and
                  Qi Cai and
                  Zhuoran Yang and
                  Zhaoran Wang},
  title        = {Neural Policy Gradient Methods: Global Optimality and Rates of Convergence},
  journal      = {CoRR},
  volume       = {abs/1909.01150},
  year         = {2019},
  url          = {http://arxiv.org/abs/1909.01150},
  eprinttype    = {arXiv},
  eprint       = {1909.01150},
  timestamp    = {Wed, 27 Dec 2023 00:00:00 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-1909-01150.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics