Jiayi Huang, Han Zhong 0001, Liwei Wang 0001, Lin Yang 0011. Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds. In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, Sergey Levine, editors, 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. 2023. [doi]
@inproceedings{Huang00023-0, title = {Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds}, author = {Jiayi Huang and Han Zhong 0001 and Liwei Wang 0001 and Lin Yang 0011}, year = {2023}, url = {http://papers.nips.cc/paper_files/paper/2023/hash/b11393733b1ea5890100302ab8a0f74c-Abstract-Conference.html}, researchr = {https://researchr.org/publication/Huang00023-0}, cites = {0}, citedby = {0}, 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}, editor = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine}, }