Graphical Minimax Game and On-Policy Reinforcement Learning for Consensus of Leaderless Multi-Agent Systems

被引：0
|
作者：
Dong, Wei [1 ]
Wang, Chunyan [1 ]
Li, Jinna [2 ,3 ]
Wang, Jianan [1 ]
机构：
[1] Beijing Inst Technol, Sch Aerosp Engn, Minist Educ, Key Lab Dynam & Control Flight Vehicle, Beijing 100081, Peoples R China
[2] Liaoning Shihua Univ, Sch Informat & Control Engn, Fushun 113001, Peoples R China
[3] Northeastern Univ, State Key Lab Synthet Automat Proc Ind, Shenyang 110819, Peoples R China
来源：
2020 IEEE 16TH INTERNATIONAL CONFERENCE ON CONTROL & AUTOMATION (ICCA) | 2020年
基金：
中国国家自然科学基金;
关键词：
LINEAR-SYSTEMS; SYNCHRONIZATION; NETWORKS;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
In this paper, we study the adaptive optimal consensus control of leaderless multi-agent systems (MASs) with heterogeneous dynamics. First, the consensus control problem is converted into a graphical minimax game problem and the corresponding algebraic Riccati equation (ARE) for each agent is obtained. Then, an on-policy reinforcement learning algorithm is proposed to online learn the optimal control policy without requiring the system dynamics. A certain rank condition is established to guarantee the convergence of the proposed online learning algorithm to the unique solution of the ARE. Finally, the effectiveness of the proposed algorithm is demonstrated through a numerical simulation.
引用
收藏
页码：606 / 611
页数：6
相关论文
共 50 条
  • [21] Maximizing Convergence Speed for Second Order Consensus in Leaderless Multi-Agent Systems
    Gianvito Difilippo
    Maria Pia Fanti
    Agostino Marcello Mangini
    IEEE/CAA Journal of Automatica Sinica, 2022, 9 (02) : 259 - 269
  • [22] Reinforcement Learning Control for Consensus of the Leader-Follower Multi-Agent Systems
    Chiang, Ming-Li
    Liu, An-Sheng
    Fu, Li-Chen
    PROCEEDINGS OF 2018 IEEE 7TH DATA DRIVEN CONTROL AND LEARNING SYSTEMS CONFERENCE (DDCLS), 2018, : 1152 - 1157
  • [23] Maximizing Convergence Speed for Second Order Consensus in Leaderless Multi-Agent Systems
    Difilippo, Gianvito
    Fanti, Maria Pia
    Mangini, Agostino Marcello
    IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2022, 9 (02) : 259 - 269
  • [24] Reinforcement Learning Consensus Control for Discrete-Time Multi-Agent Systems
    Zhu, Xiaoxia
    Yuan, Xin
    Wang, Yuanda
    Sun, Changyin
    PROCEEDINGS OF THE 38TH CHINESE CONTROL CONFERENCE (CCC), 2019, : 6178 - 6182
  • [25] Disturbance Rejection of Multi-agent Systems: A Reinforcement Learning Differential Game Approach
    Jiao, Qiang
    Modares, Hamidreza
    Xu, Shengyuan
    Lewis, Frank L.
    Vamvoudakis, Kyriakos G.
    2015 AMERICAN CONTROL CONFERENCE (ACC), 2015, : 737 - 742
  • [26] Leaderless consensus of multi-agent systems with Lipschitz nonlinear dynamics and switching topologies
    Liu, Wei
    Zhou, Shaolei
    Qi, Yahui
    Wu, Xiuzhen
    NEUROCOMPUTING, 2016, 173 : 1322 - 1329
  • [27] Distributed Leaderless Impulsive Consensus of Nonlinear Multi-Agent Systems with Input Saturation
    Liu, Xiaolu
    Wang, Zhe
    Wang, Zongchuan
    Song, Ping
    Chen, Duxin
    2019 CHINA-QATAR INTERNATIONAL WORKSHOP ON ARTIFICIAL INTELLIGENCE AND APPLICATIONS TO INTELLIGENT MANUFACTURING (AIAIM), 2019, : 36 - 41
  • [28] Guaranteed cost leaderless consensus for uncertain Markov jumping multi-agent systems
    Parivallal, A.
    Sakthivel, R.
    Wang, Chao
    JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE, 2023, 35 (02) : 257 - 273
  • [29] Differential graphical game-based multi-agent tracking control using integral reinforcement learning
    Guo, Yaning
    Sun, Qi
    Wang, Yintao
    Pan, Quan
    IET CONTROL THEORY AND APPLICATIONS, 2024, 18 (18): : 2766 - 2776
  • [30] Toward Policy Explanations for Multi-Agent Reinforcement Learning
    Boggess, Kayla
    Kraus, Sarit
    Feng, Lu
    PROCEEDINGS OF THE THIRTY-FIRST INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2022, 2022, : 109 - 115
12345