Mutual information oriented deep skill chaining for multi-agent reinforcement learning

IF 8.4 2区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Zaipeng Xie, Cheng Ji, Chentai Qiao, WenZhan Song, Zewen Li, Yufeng Zhang, Yujing Zhang
{"title":"Mutual information oriented deep skill chaining for multi-agent reinforcement learning","authors":"Zaipeng Xie,&nbsp;Cheng Ji,&nbsp;Chentai Qiao,&nbsp;WenZhan Song,&nbsp;Zewen Li,&nbsp;Yufeng Zhang,&nbsp;Yujing Zhang","doi":"10.1049/cit2.12322","DOIUrl":null,"url":null,"abstract":"<p>Multi-agent reinforcement learning relies on reward signals to guide the policy networks of individual agents. However, in high-dimensional continuous spaces, the non-stationary environment can provide outdated experiences that hinder convergence, resulting in ineffective training performance for multi-agent systems. To tackle this issue, a novel reinforcement learning scheme, Mutual Information Oriented Deep Skill Chaining (MioDSC), is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency. These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state. In addition, MioDSC can generate cooperative policies using the options framework, allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi-agent learning. MioDSC was evaluated in the multi-agent particle environment and the StarCraft multi-agent challenge at varying difficulty levels. The experimental results demonstrate that MioDSC outperforms state-of-the-art methods and is robust across various multi-agent system tasks with high stability.</p>","PeriodicalId":46211,"journal":{"name":"CAAI Transactions on Intelligence Technology","volume":"9 4","pages":"1014-1030"},"PeriodicalIF":8.4000,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1049/cit2.12322","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"CAAI Transactions on Intelligence Technology","FirstCategoryId":"94","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1049/cit2.12322","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Multi-agent reinforcement learning relies on reward signals to guide the policy networks of individual agents. However, in high-dimensional continuous spaces, the non-stationary environment can provide outdated experiences that hinder convergence, resulting in ineffective training performance for multi-agent systems. To tackle this issue, a novel reinforcement learning scheme, Mutual Information Oriented Deep Skill Chaining (MioDSC), is proposed that generates an optimised cooperative policy by incorporating intrinsic rewards based on mutual information to improve exploration efficiency. These rewards encourage agents to diversify their learning process by engaging in actions that increase the mutual information between their actions and the environment state. In addition, MioDSC can generate cooperative policies using the options framework, allowing agents to learn and reuse complex action sequences and accelerating the convergence speed of multi-agent learning. MioDSC was evaluated in the multi-agent particle environment and the StarCraft multi-agent challenge at varying difficulty levels. The experimental results demonstrate that MioDSC outperforms state-of-the-art methods and is robust across various multi-agent system tasks with high stability.

Abstract Image

面向互信息的多代理强化学习深度技能链
多代理强化学习依靠奖励信号来引导单个代理的策略网络。然而,在高维连续空间中,非稳态环境会提供过时的经验,阻碍收敛,导致多代理系统的训练效果不佳。为了解决这个问题,我们提出了一种新颖的强化学习方案--互信息导向的深度技能链(MioDSC),它通过纳入基于互信息的内在奖励来生成优化的合作策略,从而提高探索效率。这些奖励鼓励代理通过参与增加其行动与环境状态之间互信息的行动,使其学习过程多样化。此外,MioDSC 还能利用期权框架生成合作政策,允许代理学习和重复使用复杂的行动序列,加快多代理学习的收敛速度。MioDSC 在多代理粒子环境和不同难度的星际争霸多代理挑战中进行了评估。实验结果表明,MioDSC 的性能优于最先进的方法,并且在各种多代理系统任务中都具有高稳定性和鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
CAAI Transactions on Intelligence Technology
CAAI Transactions on Intelligence Technology COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE-
CiteScore
11.00
自引率
3.90%
发文量
134
审稿时长
35 weeks
期刊介绍: CAAI Transactions on Intelligence Technology is a leading venue for original research on the theoretical and experimental aspects of artificial intelligence technology. We are a fully open access journal co-published by the Institution of Engineering and Technology (IET) and the Chinese Association for Artificial Intelligence (CAAI) providing research which is openly accessible to read and share worldwide.
×
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