arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.03360cs.LGcs.AIcs.SYeess.SY
收藏

离线基于模型的强化学习综述

A Survey on Offline Model-Based Reinforcement Learning

Carnegie Mellon University(卡内基梅隆大学)

Haoyang He

AI总结:

该综述梳理了离线强化学习与基于模型的强化学习的概念及进展,聚焦二者交叉的离线基于模型强化学习领域,总结现有方法解决分布偏移问题的思路,提出领域挑战与未来研究方向。

摘要:

基于模型的方法在离线强化学习领域正日益受到青睐,由于这类模型能够借助监督学习技术充分利用已有的大规模历史数据集,因此在实际应用中具备很高的潜力。本文对离线基于模型的强化学习领域的近期研究工作展开了文献综述,该领域是将基于模型的方法应用于离线强化学习的研究方向。本综述简要概述了离线强化学习与基于模型的强化学习各自的核心概念及最新进展,并探讨了两个领域的交叉方向。随后,本文介绍了离线基于模型的强化学习领域的关键相关论文,讨论了它们的研究方法,尤其是这些方法解决分布偏移问题的思路——分布偏移是当前所有离线基于模型的强化学习方法都面临的核心问题。本文还进一步探讨了该领域面临的关键挑战,并提出了未来研究的可能方向。

英文摘要:

Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets available with supervised learning techniques. This paper presents a literature review of recent work in offline model-based reinforcement learning, a field that utilizes model-based approaches in offline reinforcement learning. The survey provides a brief overview of the concepts and recent developments in both offline reinforcement learning and model-based reinforcement learning, and discuss the intersection of the two fields. We then presents key relevant papers in the field of offline model-based reinforcement learning and discuss their methods, particularly their approaches in solving the issue of distributional shift, the main problem faced by all current offline model-based reinforcement learning methods. We further discuss key challenges faced by the field, and suggest possible directions for future work.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑