Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning

Open Webpage

Qiwei Di, Heyang Zhao, Jiafan He, Quanquan Gu

Published: 01 Jan 2024, Last Modified: 19 May 2025ICLR 2024EveryoneRevisionsBibTeXCC BY-SA 4.0