图形游戏中多干扰多智能体系统的分布式最小极大策略

IF 7.9 2区计算机科学 Q1 ENGINEERING, MULTIDISCIPLINARY

IEEE Transactions on Network Science and Engineering Pub Date : 2025-04-09 DOI:10.1109/TNSE.2025.3559028

Chunping Xiong;Qian Ma

{"title":"图形游戏中多干扰多智能体系统的分布式最小极大策略","authors":"Chunping Xiong;Qian Ma","doi":"10.1109/TNSE.2025.3559028","DOIUrl":null,"url":null,"abstract":"This paper studies the distributed minmax strategy of multi-agent systems with unknown multiple disturbances in graphical games over a network topology containing a directed spanning tree. Utilizing the sliding mode control technology and game-theoretical approaches, the distributed minmax strategy associated with the decoupled Hamilton-Jacobi-Isaacs equations are derived. To solve the strategy, an effective method based on reinforcement learning and neural network approximation is proposed in which the condition of persistent excitation is relaxed and the requirement of initial stabilizing control is removed. By Lyapunov stability theory, it is proven that under the proposed minmax strategy, the consensus error systems are asymptotically stable and the sliding mode dynamics exhibit <inline-formula><tex-math>$\\mathcal {L}_{2}$</tex-math></inline-formula>-gain stability. Finally, a numerical illustration is presented to demonstrate the effectiveness of the theoretical analysis.","PeriodicalId":54229,"journal":{"name":"IEEE Transactions on Network Science and Engineering","volume":"12 4","pages":"3286-3298"},"PeriodicalIF":7.9000,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Distributed Minmax Strategy for Multi-Agent Systems With Multiple Disturbances in Graphical Games\",\"authors\":\"Chunping Xiong;Qian Ma\",\"doi\":\"10.1109/TNSE.2025.3559028\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper studies the distributed minmax strategy of multi-agent systems with unknown multiple disturbances in graphical games over a network topology containing a directed spanning tree. Utilizing the sliding mode control technology and game-theoretical approaches, the distributed minmax strategy associated with the decoupled Hamilton-Jacobi-Isaacs equations are derived. To solve the strategy, an effective method based on reinforcement learning and neural network approximation is proposed in which the condition of persistent excitation is relaxed and the requirement of initial stabilizing control is removed. By Lyapunov stability theory, it is proven that under the proposed minmax strategy, the consensus error systems are asymptotically stable and the sliding mode dynamics exhibit <inline-formula><tex-math>$\\\\mathcal {L}_{2}$</tex-math></inline-formula>-gain stability. Finally, a numerical illustration is presented to demonstrate the effectiveness of the theoretical analysis.\",\"PeriodicalId\":54229,\"journal\":{\"name\":\"IEEE Transactions on Network Science and Engineering\",\"volume\":\"12 4\",\"pages\":\"3286-3298\"},\"PeriodicalIF\":7.9000,\"publicationDate\":\"2025-04-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Transactions on Network Science and Engineering\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://ieeexplore.ieee.org/document/10959064/\",\"RegionNum\":2,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Network Science and Engineering","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10959064/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

摘要

在包含有向生成树的网络拓扑结构上，研究了图形游戏中具有未知多重干扰的多智能体系统的分布式最小最大策略。利用滑模控制技术和博弈论方法，推导了与解耦Hamilton-Jacobi-Isaacs方程相关的分布式极大极小策略。为了解决该策略，提出了一种基于强化学习和神经网络逼近的有效方法，该方法放宽了持续激励的条件，消除了初始稳定控制的要求。利用Lyapunov稳定性理论，证明了在极小极大策略下，系统是渐近稳定的，滑模动力学表现出$\mathcal {L}_{2}$-增益稳定性。最后，通过数值算例验证了理论分析的有效性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Distributed Minmax Strategy for Multi-Agent Systems With Multiple Disturbances in Graphical Games

This paper studies the distributed minmax strategy of multi-agent systems with unknown multiple disturbances in graphical games over a network topology containing a directed spanning tree. Utilizing the sliding mode control technology and game-theoretical approaches, the distributed minmax strategy associated with the decoupled Hamilton-Jacobi-Isaacs equations are derived. To solve the strategy, an effective method based on reinforcement learning and neural network approximation is proposed in which the condition of persistent excitation is relaxed and the requirement of initial stabilizing control is removed. By Lyapunov stability theory, it is proven that under the proposed minmax strategy, the consensus error systems are asymptotically stable and the sliding mode dynamics exhibit

$\mathcal {L}_{2}$

-gain stability. Finally, a numerical illustration is presented to demonstrate the effectiveness of the theoretical analysis.

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

IEEE Transactions on Network Science and Engineering Engineering-Control and Systems Engineering

CiteScore

12.60

自引率

9.10%

发文量

393

期刊介绍： The proposed journal, called the IEEE Transactions on Network Science and Engineering (TNSE), is committed to timely publishing of peer-reviewed technical articles that deal with the theory and applications of network science and the interconnections among the elements in a system that form a network. In particular, the IEEE Transactions on Network Science and Engineering publishes articles on understanding, prediction, and control of structures and behaviors of networks at the fundamental level. The types of networks covered include physical or engineered networks, information networks, biological networks, semantic networks, economic networks, social networks, and ecological networks. Aimed at discovering common principles that govern network structures, network functionalities and behaviors of networks, the journal seeks articles on understanding, prediction, and control of structures and behaviors of networks. Another trans-disciplinary focus of the IEEE Transactions on Network Science and Engineering is the interactions between and co-evolution of different genres of networks.