arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.01072cs.AI
收藏

强化学习中的自博弈方法综述

A Survey on Self-play Methods in Reinforcement Learning

Tsinghua University(清华大学);Peking University(北京大学);Tencent(腾讯)

Ruize Zhang, Zelai Xu, Chengdong Ma, Chao Yu, Wei-Wei Tu, Wenhao Tang, Shiyu Huang, Deheng Ye, Wenbo Ding, Yaodong Yang, Yu Wang

AI总结:

本文综述强化学习中的自博弈方法,提出统一分类框架,梳理其在非合作 MARL 场景中的算法、应用及未来挑战。

摘要:

自博弈是一种学习范式,在该范式中,智能体通过与自身或其他不断演化的智能体的历史版本或同时期版本进行交互,迭代地改进其策略;它已在解决复杂的非合作多智能体任务方面取得显著成功。尽管自博弈在多智能体强化学习(MARL)中的重要性日益增长,例如在围棋、扑克和电子游戏中,但对自博弈仍缺乏全面且结构化的理解。本综述通过为多样化的自博弈方法图景提供一份全面路线图来填补这一空白。我们首先介绍必要的预备知识,包括 MARL 框架和基础博弈论概念。随后,本文给出一个统一框架,并在该框架内对现有自博弈算法进行分类。此外,本文通过阐述自博弈在不同非合作场景中的作用,弥合算法与其实际意义之间的差距。最后,本综述强调自博弈中的开放性挑战和未来研究方向。

英文摘要:

Self-play, a learning paradigm where agents iteratively refine their policies by interacting with historical or concurrent versions of themselves or other evolving agents, has shown remarkable success in solving complex non-cooperative multi-agent tasks. Despite its growing prominence in multi-agent reinforcement learning (MARL), such as Go, poker, and video games, a comprehensive and structured understanding of self-play remains lacking. This survey fills this gap by offering a comprehensive roadmap to the diverse landscape of self-play methods. We begin by introducing the necessary preliminaries, including the MARL framework and basic game theory concepts. Then, it provides a unified framework and classifies existing self-play algorithms within this framework. Moreover, the paper bridges the gap between the algorithms and their practical implications by illustrating the role of self-play in different non-cooperative scenarios. Finally, the survey highlights open challenges and future research directions in self-play.

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。

↑