Near-optimal Offline Reinforcement Learning with Linear Representation: Leveraging Variance Information with Pessimism

Open Webpage

Ming Yin, Yaqi Duan, Mengdi Wang, Yu-Xiang Wang

Published: 01 Jan 2022, Last Modified: 23 May 2024ICLR 2022EveryoneRevisionsBibTeXCC BY-SA 4.0