Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms

强化学习 泥灰岩 计算机科学 人工智能 领域(数学) 机器学习 趋同(经济学) 管理科学 数学 工程类 经济增长 生物 构造盆地 古生物学 经济 纯数学
作者
Kaiqing Zhang,Zhuoran Yang,Tamer Başar
出处
期刊:Studies in systems, decision and control [Springer International Publishing]
卷期号:: 321-384 被引量:1136
标识
DOI:10.1007/978-3-030-60990-0_12
摘要

Recent years have witnessed significant advances in reinforcement learning (RL), which has registered tremendous success in solving various sequential decision-making problems in machine learning. Most of the successful RL applications, e.g., the games of Go and Poker, robotics, and autonomous driving, involve the participation of more than one single agent, which naturally fall into the realm of multi-agent RL (MARL), a domain with a relatively long history, and has recently re-emerged due to advances in single-agent RL techniques. Though empirically successful, theoretical foundations for MARL are relatively lacking in the literature. In this chapter, we provide a selective overview of MARL, with focus on algorithms backed by theoretical analysis. More specifically, we review the theoretical results of MARL algorithms mainly within two representative frameworks, Markov/stochastic games and extensive-form games, in accordance with the types of tasks they address, i.e., fully cooperative, fully competitive, and a mix of the two. We also introduce several significant but challenging applications of these algorithms. Orthogonal to the existing reviews on MARL, we highlight several new angles and taxonomies of MARL theory, including learning in extensive-form games, decentralized MARL with networked agents, MARL in the mean-field regime, (non-)convergence of policy-based methods for learning in games, etc. Some of the new angles extrapolate from our own research endeavors and interests. Our overall goal with this chapter is, beyond providing an assessment of the current state of the field on the mark, to identify fruitful future research directions on theoretical studies of MARL. We expect this chapter to serve as continuing stimulus for researchers interested in working on this exciting while challenging topic.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
图图完成签到,获得积分10
刚刚
XHW完成签到,获得积分10
刚刚
刚刚
muyu完成签到,获得积分10
刚刚
1秒前
科研通AI6.2的应助被YYYYao11采纳,获得10
1秒前
吃鱼完成签到,获得积分10
1秒前
肖一一发布了新的文献求助10
1秒前
木叶完成签到,获得积分10
1秒前
慕容博完成签到,获得积分10
1秒前
1秒前
Maestro_S发布了新的文献求助50
1秒前
1秒前
阿拉斯嘉完成签到,获得积分10
1秒前
要减肥的姝完成签到 ,获得积分10
1秒前
李木子发布了新的文献求助10
2秒前
勤劳半青完成签到,获得积分0
2秒前
所所的应助被落寞的茉莉采纳,获得10
2秒前
redred发布了新的文献求助10
3秒前
3秒前
周俊雄发布了新的文献求助10
3秒前
淡然的山水完成签到,获得积分10
3秒前
搜集达人的应助被pk采纳,获得10
4秒前
欣喜的剑封完成签到,获得积分10
4秒前
cyd123完成签到,获得积分10
4秒前
Nancy发布了新的文献求助10
4秒前
贪玩的秋柔的应助被yc采纳,获得10
5秒前
畅快的饼干完成签到 ,获得积分10
5秒前
Nat完成签到,获得积分10
5秒前
6秒前
18707979012发布了新的文献求助10
6秒前
syr发布了新的文献求助20
6秒前
水木公发布了新的文献求助10
6秒前
tangyimmo完成签到,获得积分10
6秒前
6秒前
狂野从蕾完成签到 ,获得积分10
6秒前
7秒前
LWDYF完成签到,获得积分10
7秒前
7秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8160268
求助须知:如何正确求助?哪些是违规求助? 9555328
关于积分的说明 21727231
捐赠科研通 7750062
什么是DOI,文献DOI怎么找? 3427353
关于科研通互助平台的介绍 2552391
邀请新用户注册赠送积分活动 2471707