{"title":"具有交互和任务表征的多任务多代理强化学习","authors":"Chao Li, Shaokang Dong, Shangdong Yang, Yujing Hu, Tianyu Ding, Wenbin Li, Yang Gao","doi":"10.1109/TNNLS.2024.3475216","DOIUrl":null,"url":null,"abstract":"<p><p>Multi-task multi-agent reinforcement learning (MT-MARL) is capable of leveraging useful knowledge across multiple related tasks to improve performance on any single task. While recent studies have tentatively achieved this by learning independent policies on a shared representation space, we pinpoint that further advancements can be realized by explicitly characterizing agent interactions within these multi-agent tasks and identifying task relations for selective reuse. To this end, this article proposes Representing Interactions and Tasks (RIT), a novel MT-MARL algorithm that characterizes both intra-task agent interactions and inter-task task relations. Specifically, for characterizing agent interactions, RIT presents the interactive value decomposition to explicitly take the dependency among agents into policy learning. Theoretical analysis demonstrates that the learned utility value of each agent approximates its Shapley value, thus representing agent interactions. Moreover, we learn task representations based on per-agent local trajectories, which assess task similarities and accordingly identify task relations. As a result, RIT facilitates the effective transfer of interaction knowledge across similar multi-agent tasks. Structurally, RIT develops universal policy structure for scalable multi-task policy learning. We evaluate RIT against multiple state-of-the-art baselines in various cooperative tasks, and its significant performance under both multi-task and zero-shot settings demonstrates its effectiveness.</p>","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":10.2000,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations.\",\"authors\":\"Chao Li, Shaokang Dong, Shangdong Yang, Yujing Hu, Tianyu Ding, Wenbin Li, Yang Gao\",\"doi\":\"10.1109/TNNLS.2024.3475216\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Multi-task multi-agent reinforcement learning (MT-MARL) is capable of leveraging useful knowledge across multiple related tasks to improve performance on any single task. While recent studies have tentatively achieved this by learning independent policies on a shared representation space, we pinpoint that further advancements can be realized by explicitly characterizing agent interactions within these multi-agent tasks and identifying task relations for selective reuse. To this end, this article proposes Representing Interactions and Tasks (RIT), a novel MT-MARL algorithm that characterizes both intra-task agent interactions and inter-task task relations. Specifically, for characterizing agent interactions, RIT presents the interactive value decomposition to explicitly take the dependency among agents into policy learning. Theoretical analysis demonstrates that the learned utility value of each agent approximates its Shapley value, thus representing agent interactions. Moreover, we learn task representations based on per-agent local trajectories, which assess task similarities and accordingly identify task relations. As a result, RIT facilitates the effective transfer of interaction knowledge across similar multi-agent tasks. Structurally, RIT develops universal policy structure for scalable multi-task policy learning. We evaluate RIT against multiple state-of-the-art baselines in various cooperative tasks, and its significant performance under both multi-task and zero-shot settings demonstrates its effectiveness.</p>\",\"PeriodicalId\":13303,\"journal\":{\"name\":\"IEEE transactions on neural networks and learning systems\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":10.2000,\"publicationDate\":\"2024-10-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE transactions on neural networks and learning systems\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://doi.org/10.1109/TNNLS.2024.3475216\",\"RegionNum\":1,\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE transactions on neural networks and learning systems","FirstCategoryId":"94","ListUrlMain":"https://doi.org/10.1109/TNNLS.2024.3475216","RegionNum":1,"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
摘要
多任务多代理强化学习(MT-MARL)能够利用多个相关任务中的有用知识来提高任何单一任务的性能。虽然最近的研究通过在共享表示空间上学习独立策略初步实现了这一目标,但我们认为,通过明确描述这些多代理任务中的代理交互,并识别任务关系以进行选择性重用,可以实现进一步的进步。为此,本文提出了 "交互与任务表征"(Representing Interactions and Tasks,RIT),这是一种新型 MT-MARL 算法,可表征任务内的代理交互和任务间的任务关系。具体来说,为了表征代理交互,RIT 提出了交互值分解,明确地将代理之间的依赖关系纳入策略学习。理论分析表明,每个代理的学习效用值近似于其 Shapley 值,从而代表了代理之间的交互。此外,我们根据每个代理的局部轨迹学习任务表征,从而评估任务的相似性,并相应地确定任务关系。因此,RIT 可促进交互知识在类似多代理任务中的有效转移。在结构上,RIT 为可扩展的多任务策略学习开发了通用策略结构。我们在各种合作任务中对照多个最先进的基线对 RIT 进行了评估,其在多任务和零次任务设置下的显著表现证明了它的有效性。
Multi-Task Multi-Agent Reinforcement Learning With Interaction and Task Representations.
Multi-task multi-agent reinforcement learning (MT-MARL) is capable of leveraging useful knowledge across multiple related tasks to improve performance on any single task. While recent studies have tentatively achieved this by learning independent policies on a shared representation space, we pinpoint that further advancements can be realized by explicitly characterizing agent interactions within these multi-agent tasks and identifying task relations for selective reuse. To this end, this article proposes Representing Interactions and Tasks (RIT), a novel MT-MARL algorithm that characterizes both intra-task agent interactions and inter-task task relations. Specifically, for characterizing agent interactions, RIT presents the interactive value decomposition to explicitly take the dependency among agents into policy learning. Theoretical analysis demonstrates that the learned utility value of each agent approximates its Shapley value, thus representing agent interactions. Moreover, we learn task representations based on per-agent local trajectories, which assess task similarities and accordingly identify task relations. As a result, RIT facilitates the effective transfer of interaction knowledge across similar multi-agent tasks. Structurally, RIT develops universal policy structure for scalable multi-task policy learning. We evaluate RIT against multiple state-of-the-art baselines in various cooperative tasks, and its significant performance under both multi-task and zero-shot settings demonstrates its effectiveness.
期刊介绍:
The focus of IEEE Transactions on Neural Networks and Learning Systems is to present scholarly articles discussing the theory, design, and applications of neural networks as well as other learning systems. The journal primarily highlights technical and scientific research in this domain.