多代理合作强化学习中分散执行的集中训练简介

Christopher Amato
{"title":"多代理合作强化学习中分散执行的集中训练简介","authors":"Christopher Amato","doi":"arxiv-2409.03052","DOIUrl":null,"url":null,"abstract":"Multi-agent reinforcement learning (MARL) has exploded in popularity in\nrecent years. Many approaches have been developed but they can be divided into\nthree main types: centralized training and execution (CTE), centralized\ntraining for decentralized execution (CTDE), and Decentralized training and\nexecution (DTE). CTDE methods are the most common as they can use centralized information\nduring training but execute in a decentralized manner -- using only information\navailable to that agent during execution. CTDE is the only paradigm that\nrequires a separate training phase where any available information (e.g., other\nagent policies, underlying states) can be used. As a result, they can be more\nscalable than CTE methods, do not require communication during execution, and\ncan often perform well. CTDE fits most naturally with the cooperative case, but\ncan be potentially applied in competitive or mixed settings depending on what\ninformation is assumed to be observed. This text is an introduction to CTDE in cooperative MARL. It is meant to\nexplain the setting, basic concepts, and common methods. It does not cover all\nwork in CTDE MARL as the subarea is quite extensive. I have included work that\nI believe is important for understanding the main concepts in the subarea and\napologize to those that I have omitted.","PeriodicalId":501315,"journal":{"name":"arXiv - CS - Multiagent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning\",\"authors\":\"Christopher Amato\",\"doi\":\"arxiv-2409.03052\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multi-agent reinforcement learning (MARL) has exploded in popularity in\\nrecent years. Many approaches have been developed but they can be divided into\\nthree main types: centralized training and execution (CTE), centralized\\ntraining for decentralized execution (CTDE), and Decentralized training and\\nexecution (DTE). CTDE methods are the most common as they can use centralized information\\nduring training but execute in a decentralized manner -- using only information\\navailable to that agent during execution. CTDE is the only paradigm that\\nrequires a separate training phase where any available information (e.g., other\\nagent policies, underlying states) can be used. As a result, they can be more\\nscalable than CTE methods, do not require communication during execution, and\\ncan often perform well. CTDE fits most naturally with the cooperative case, but\\ncan be potentially applied in competitive or mixed settings depending on what\\ninformation is assumed to be observed. This text is an introduction to CTDE in cooperative MARL. It is meant to\\nexplain the setting, basic concepts, and common methods. It does not cover all\\nwork in CTDE MARL as the subarea is quite extensive. I have included work that\\nI believe is important for understanding the main concepts in the subarea and\\napologize to those that I have omitted.\",\"PeriodicalId\":501315,\"journal\":{\"name\":\"arXiv - CS - Multiagent Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-04\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Multiagent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.03052\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Multiagent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.03052","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

多代理强化学习(MARL)近年来大受欢迎。目前已开发出许多方法,但主要可分为三类:集中训练和执行(CTE)、集中训练分散执行(CTDE)和分散训练和执行(DTE)。CTDE 方法是最常见的方法,因为它们可以在训练期间使用集中信息,但以分散方式执行--在执行期间仅使用该代理可用的信息。CTDE 是唯一一种需要单独训练阶段的模式,在训练阶段可以使用任何可用信息(如其他代理策略、底层状态)。因此,它们比 CTE 方法更具可扩展性,不需要在执行过程中进行通信,而且通常性能良好。CTDE 最自然地适用于合作情况,但也有可能应用于竞争或混合情况,这取决于假定观察到哪些信息。本文介绍了合作 MARL 中的 CTDE。它旨在解释设置、基本概念和常用方法。它并不涵盖 CTDE MARL 中的所有工作,因为该子领域相当广泛。我收录了我认为对理解该子领域主要概念非常重要的工作,并对遗漏的工作表示歉意。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
An Introduction to Centralized Training for Decentralized Execution in Cooperative Multi-Agent Reinforcement Learning
Multi-agent reinforcement learning (MARL) has exploded in popularity in recent years. Many approaches have been developed but they can be divided into three main types: centralized training and execution (CTE), centralized training for decentralized execution (CTDE), and Decentralized training and execution (DTE). CTDE methods are the most common as they can use centralized information during training but execute in a decentralized manner -- using only information available to that agent during execution. CTDE is the only paradigm that requires a separate training phase where any available information (e.g., other agent policies, underlying states) can be used. As a result, they can be more scalable than CTE methods, do not require communication during execution, and can often perform well. CTDE fits most naturally with the cooperative case, but can be potentially applied in competitive or mixed settings depending on what information is assumed to be observed. This text is an introduction to CTDE in cooperative MARL. It is meant to explain the setting, basic concepts, and common methods. It does not cover all work in CTDE MARL as the subarea is quite extensive. I have included work that I believe is important for understanding the main concepts in the subarea and apologize to those that I have omitted.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Putting Data at the Centre of Offline Multi-Agent Reinforcement Learning HARP: Human-Assisted Regrouping with Permutation Invariant Critic for Multi-Agent Reinforcement Learning On-policy Actor-Critic Reinforcement Learning for Multi-UAV Exploration CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark Multi-agent Path Finding in Continuous Environment
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1