Zihan Zhang, Xiangyang Ji, Simon S. Du. Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies. In Po-Ling Loh, Maxim Raginsky, editors, Conference on Learning Theory, 2-5 July 2022, London, UK. Volume 178 of Proceedings of Machine Learning Research, pages 3858-3904, PMLR, 2022. [doi]
@inproceedings{ZhangJD22-0,
title = {Horizon-Free Reinforcement Learning in Polynomial Time: the Power of Stationary Policies},
author = {Zihan Zhang and Xiangyang Ji and Simon S. Du},
year = {2022},
url = {https://proceedings.mlr.press/v178/zhang22a.html},
researchr = {https://researchr.org/publication/ZhangJD22-0},
cites = {0},
citedby = {0},
pages = {3858-3904},
booktitle = {Conference on Learning Theory, 2-5 July 2022, London, UK},
editor = {Po-Ling Loh and Maxim Raginsky},
volume = {178},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}