Xiaoyan Hu, Ho-Fung Leung. A Tighter Problem-Dependent Regret Bound for Risk-Sensitive Reinforcement Learning. In Francisco J. R. Ruiz, Jennifer G. Dy, Jan-Willem van de Meent, editors, International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain. Volume 206 of Proceedings of Machine Learning Research, pages 5411-5437, PMLR, 2023. [doi]
@inproceedings{HuL23-8,
title = {A Tighter Problem-Dependent Regret Bound for Risk-Sensitive Reinforcement Learning},
author = {Xiaoyan Hu and Ho-Fung Leung},
year = {2023},
url = {https://proceedings.mlr.press/v206/hu23b.html},
researchr = {https://researchr.org/publication/HuL23-8},
cites = {0},
citedby = {0},
pages = {5411-5437},
booktitle = {International Conference on Artificial Intelligence and Statistics, 25-27 April 2023, Palau de Congressos, Valencia, Spain},
editor = {Francisco J. R. Ruiz and Jennifer G. Dy and Jan-Willem van de Meent},
volume = {206},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}