Optimal Tracking Control of Heterogeneous Multi-agent Systems with Switching Topology via Actor-Critic Neural Networks
作者单位：School of Automation Engineering University of Electronic Science and Technology of China Department of Mathematics and StatisticsTexas Tech University
会议名称：《第37届中国控制会议》
会议日期：2018年
学科分类：0711[理学-系统科学] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 071102[理学-系统分析与集成] 081103[工学-系统工程]
基 金：partially supported by National Natural Science Foundation of China under Grants No.61473061,No.61104104 the Program for New Century Excellent Talents in University under Grant No.NCET-13-0091
关 键 词：Optimal tracking control multi-agent systems adaptive dynamic programming actor-critic neural network
摘 要：In this paper, an optimal tracking control problem is solved for high-order heterogeneous multi-agent systems with time-varying interaction networks within the framework of reinforcement learning. First, the optimal tracking control problem is formulated as a leader-follower multi-agent system. Second, a policy iteration based adaptive dynamic programming（ADP） algorithm is proposed to compute the performance index and the control law. Furthermore, the convergence to the optimal solutions is analyzed for the proposed algorithm. Third, an actor-critic neural network is applied to approximate the iterative performance index function and the control law, which implement the policy iteration algorithm online without using the knowledge of the system dynamics. Finally, some simulation results are presented to demonstrate the proposed optimal tracking control strategy.