多智能体强化学习中多个独立顾问的学习

Sriram Ganapathi Subramanian, Matthew E. Taylor, K. Larson, Mark Crowley
{"title":"多智能体强化学习中多个独立顾问的学习","authors":"Sriram Ganapathi Subramanian, Matthew E. Taylor, K. Larson, Mark Crowley","doi":"10.48550/arXiv.2301.11153","DOIUrl":null,"url":null,"abstract":"Multi-agent reinforcement learning typically suffers from the problem of sample inefficiency, where learning suitable policies involves the use of many data samples. Learning from external demonstrators is a possible solution that mitigates this problem. However, most prior approaches in this area assume the presence of a single demonstrator. Leveraging multiple knowledge sources (i.e., advisors) with expertise in distinct aspects of the environment could substantially speed up learning in complex environments. This paper considers the problem of simultaneously learning from multiple independent advisors in multi-agent reinforcement learning. The approach leverages a two-level Q-learning architecture, and extends this framework from single-agent to multi-agent settings. We provide principled algorithms that incorporate a set of advisors by both evaluating the advisors at each state and subsequently using the advisors to guide action selection. We also provide theoretical convergence and sample complexity guarantees. Experimentally, we validate our approach in three different test-beds and show that our algorithms give better performances than baselines, can effectively integrate the combined expertise of different advisors, and learn to ignore bad advice.","PeriodicalId":326727,"journal":{"name":"Adaptive Agents and Multi-Agent Systems","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-01-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning\",\"authors\":\"Sriram Ganapathi Subramanian, Matthew E. Taylor, K. Larson, Mark Crowley\",\"doi\":\"10.48550/arXiv.2301.11153\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Multi-agent reinforcement learning typically suffers from the problem of sample inefficiency, where learning suitable policies involves the use of many data samples. Learning from external demonstrators is a possible solution that mitigates this problem. However, most prior approaches in this area assume the presence of a single demonstrator. Leveraging multiple knowledge sources (i.e., advisors) with expertise in distinct aspects of the environment could substantially speed up learning in complex environments. This paper considers the problem of simultaneously learning from multiple independent advisors in multi-agent reinforcement learning. The approach leverages a two-level Q-learning architecture, and extends this framework from single-agent to multi-agent settings. We provide principled algorithms that incorporate a set of advisors by both evaluating the advisors at each state and subsequently using the advisors to guide action selection. We also provide theoretical convergence and sample complexity guarantees. Experimentally, we validate our approach in three different test-beds and show that our algorithms give better performances than baselines, can effectively integrate the combined expertise of different advisors, and learn to ignore bad advice.\",\"PeriodicalId\":326727,\"journal\":{\"name\":\"Adaptive Agents and Multi-Agent Systems\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-01-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Adaptive Agents and Multi-Agent Systems\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2301.11153\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Adaptive Agents and Multi-Agent Systems","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2301.11153","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

多智能体强化学习通常存在样本效率低下的问题,其中学习合适的策略涉及使用许多数据样本。向外部示范人员学习是缓解这一问题的可能解决方案。然而,该领域的大多数先前方法都假定存在单个演示者。利用具有环境不同方面专业知识的多个知识来源(例如,顾问)可以大大加快复杂环境中的学习速度。本文研究了多智能体强化学习中同时向多个独立顾问学习的问题。该方法利用两级q学习架构,并将该框架从单智能体扩展到多智能体设置。我们提供有原则的算法,通过评估每个状态的顾问,并随后使用顾问来指导行动选择,将一组顾问合并在一起。我们还提供了理论收敛性和样本复杂度保证。实验中,我们在三个不同的测试平台上验证了我们的方法,并表明我们的算法比基线提供了更好的性能,可以有效地整合不同顾问的综合专业知识,并学会忽略糟糕的建议。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Learning from Multiple Independent Advisors in Multi-agent Reinforcement Learning
Multi-agent reinforcement learning typically suffers from the problem of sample inefficiency, where learning suitable policies involves the use of many data samples. Learning from external demonstrators is a possible solution that mitigates this problem. However, most prior approaches in this area assume the presence of a single demonstrator. Leveraging multiple knowledge sources (i.e., advisors) with expertise in distinct aspects of the environment could substantially speed up learning in complex environments. This paper considers the problem of simultaneously learning from multiple independent advisors in multi-agent reinforcement learning. The approach leverages a two-level Q-learning architecture, and extends this framework from single-agent to multi-agent settings. We provide principled algorithms that incorporate a set of advisors by both evaluating the advisors at each state and subsequently using the advisors to guide action selection. We also provide theoretical convergence and sample complexity guarantees. Experimentally, we validate our approach in three different test-beds and show that our algorithms give better performances than baselines, can effectively integrate the combined expertise of different advisors, and learn to ignore bad advice.
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
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信