摘要
多智能体对抗系统是多方博弈的复杂系统。近年来,很多研究聚焦于用强化学习解决多智能体对抗博弈问题。文章从多智能体强化学习的角度对智能博弈对抗的算法进行综述。首先,简要介绍了对多智能体强化学习及博弈论;然后,提出多智能体强化学习的4项关键技术难点,并提出相关解决方法;最后,归纳多智能体强化学习的前沿研究方向,总结了研究热点与存在的挑战。综述为后续的研究打下基础,为使用多智能体强化学习解决博弈对抗问题提供思路。
Multi-agent adversarial systems are complex multi-perty game systems,and in recent years,many studies have focused on using reinforcement learning to solve multi-agent adversarial game problems.This article reviews intelligent game adversarial algorithms from the perspective of multi-agent reinforcement learning.First,a brief introduction to multi-agent reinforcement learning and game theory is given;then,four key technical difficulties of multi-agent reinforcement learning are proposed,and related solutions are sorted out;finally,the frontier research direction of multi-agent reinforcement learning is summarized,and three research hotspots and challenges are concluded.This review lays a foundation for the subsequent research and provides ideas for solving the game antagonism problem by using multi-agent reinforcement learning.
作者
张耐民
蔡秉辰
于浛
刘海阔
ZHANG Naimin;CAI Bingchen;YU Han;LIU Haikuo(Beijing Institute of Astronautical Systems Engineering,Beijing,100076,China;School of Automation,Beijing Institute of Technology,Beijing,100081,China)
出处
《海军航空大学学报》
2024年第4期395-410,共16页
Journal of Naval Aviation University
基金
国家自然科学基金(92371207)。
关键词
多智能体
强化学习
博弈论
multi-agent
reinforcement learning
game theory