Achieving the Asymptotically Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach

Yue Wang 0068, Jinjun Xiong, Shaofeng Zou. Achieving the Asymptotically Minimax Optimal Sample Complexity of Offline Reinforcement Learning: A DRO-Based Approach. Trans. Mach. Learn. Res., 2024, 2024. [doi]

Abstract

Abstract is missing.