Paper recorded by Signals 4 on 2026-10-13 in cs.AI. Abstract reproduced from arXiv; link to the original below.
Published 2026-10-13 on arXiv · recorded by Signals 4 on 2026-10-14
Category: cs.AI · 人工智能 · first seen 2026-10-14
This paper investigates offline Q-learning for finite-horizon Markov decision processes with Kullback-Leibler (KL) regularization. Recent studies have shown that KL regularization can yield fast rates in offline decision-making problems. However, it remains unclear whether Q-learning, which adopts incremental stochastic approximation updates, can achieve such fast rates in the offline setting. We