Multi-Agent Differential Graphical Games: Nash Online Adaptive Learning Solutions

被引：0

作者：

Abouheaf, Mohammed I. ^{[1
]}

Lewis, Frank L. ^{[1
]}

机构：

[1] Univ Texas Arlington, Res Inst, Arlington, TX 76019 USA

来源：

2013 IEEE 52ND ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC) | 2013年

关键词：

Critic network structures; graphical games; integral reinforcement learning; optimal control; COOPERATIVE CONTROL; CONSENSUS; SYNCHRONIZATION; NETWORKS; SYSTEMS;

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：

This paper studies a class of multi-agent graphical games denoted by differential graphical games, where interactions between agents are prescribed by a communication graph structure. Ideas from cooperative control are given to achieve synchronization among the agents to a leader dynamics. New coupled Bellman and Hamilton-Jacobi-Bellman equations are developed for this class of games using Integral Reinforcement Learning. Nash solutions are given in terms of solutions to a set of coupled continuous-time Hamilton-Jacobi-Bellman equations. A multi-agent policy iteration algorithm is given to learn the Nash solution in real time without knowing the complete dynamic models of the agents. A proof of convergence for this algorithm is given. An online multi-agent method based on policy iterations is developed using a critic network to solve all the Hamilton-Jacobi-Bellman equations simultaneously for the graphical game.

引用

页码：5803 / 5809

页数：7

共 50 条

[21] Distributed Nash equilibrium solution for multi-agent game in adversarial environment: A reinforcement learning method [J].

Liu, Qiwei ;

Yan, Huaicheng ;

Chen, Kaitian ;

Wang, Meng ;

Li, Zhichen .

AUTOMATICA, 2025, 178

[22] Optimal Robust Formation of Multi-Agent Systems as Adversarial Graphical Apprentice Games With Inverse Reinforcement Learning [J].

Golmisheh, Fatemeh Mahdavi ;

Shamaghdari, Saeed .

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING, 2025, 22 :4867-4880

[23] Approximate Dynamic Programming Solutions of Multi-Agent Graphical Games Using Actor-Critic Network Structures [J].

Abouheaf, Mohammed I. ;

Lewis, Frank L. .

2013 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2013,

[24] Adaptive impulsive consensus of multi-agent systems with unknown parameters [J].

Xiao, Peng ;

Ma, Tiedong ;

Xue, Fangzheng ;

Gu, Zhenyu ;

Fu, Jie .

PROCEEDINGS OF THE 28TH CHINESE CONTROL AND DECISION CONFERENCE (2016 CCDC), 2016, :1741-1746

[25] Differential inequalities in multi-agent coordination and opinion dynamics modeling [J].

Proskurnikov, Anton V. ;

Cao, Ming .

AUTOMATICA, 2017, 85 :202-210

[26] Distributed consensus of linear multi-agent systems with adaptive dynamic protocols [J].

Li, Zhongkui ;

Ren, Wei ;

Liu, Xiangdong ;

Xie, Lihua .

AUTOMATICA, 2013, 49 (07) :1986-1995

[27] Task assignment in multi-agent games via reinforcement learning [J].

Li, ShangHeng ;

Liu, Hao ;

Ren, ZiMing ;

Li, YaFan ;

Liu, DaWei .

Scientia Sinica Technologica, 2025, 55 (05) :906-913

[28] Consensus of nonlinear multi-agent systems with adaptive protocols [J].

Wang, Lei ;

Feng, Wei-jie ;

Chen, Michael Z. Q. ;

Wang, Qing-guo .

IET CONTROL THEORY AND APPLICATIONS, 2014, 8 (18) :2245-2252

[29] Synchronization of Heterogeneous Multi-Agent Systems by Adaptive Iterative Learning Control [J].

Yang, Shiping ;

Xu, Jian-Xin ;

Huang, Deqing ;

Tan, Ying .

ASIAN JOURNAL OF CONTROL, 2015, 17 (06) :2091-2104

[30] Model-Free Adaptive Learning Solutions for Discrete-Time Dynamic Graphical Games [J].

Abouheaf, Mohammed I. ;

Lewis, Frank L. ;

Mahmoud, Magdi S. .

2014 IEEE 53RD ANNUAL CONFERENCE ON DECISION AND CONTROL (CDC), 2014, :3578-3583

← 1 2 3 4 5 →