Heyang Zhao, Jiafan He, Dongruo Zhou, Tong Zhang, Quanquan Gu. Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency. In Gergely Neu, Lorenzo Rosasco, editors, The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India. Volume 195 of Proceedings of Machine Learning Research, pages 4977-5020, PMLR, 2023. [doi]
@inproceedings{ZhaoHZZG23,
title = {Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency},
author = {Heyang Zhao and Jiafan He and Dongruo Zhou and Tong Zhang and Quanquan Gu},
year = {2023},
url = {https://proceedings.mlr.press/v195/zhao23a.html},
researchr = {https://researchr.org/publication/ZhaoHZZG23},
cites = {0},
citedby = {0},
pages = {4977-5020},
booktitle = {The Thirty Sixth Annual Conference on Learning Theory, 12-15 July 2023, Bangalore, India},
editor = {Gergely Neu and Lorenzo Rosasco},
volume = {195},
series = {Proceedings of Machine Learning Research},
publisher = {PMLR},
}