TY - GEN
T1 - Optimal Tracking Control of Heterogeneous Multi-agent Systems with Switching Topology Via Actor-Critic Neural Networks
AU - Peng, Zhinan
AU - Hu, Jiangping
AU - Ghosh, Bijoy K.
N1 - Funding Information:
This work is partially supported by National Natural Science Foundation of China under Grants No. 61473061, No. 61104104 and the Program for New Century Excellent Talents in University under Grant No. NCET-13-0091.
Funding Information:
This work is partially supported by National Natural Science Foundation of China under Grants No. 61473061, No. 61104104 and the Program for New Century Excellent Talents in University under Grant No. NCET-13-0091
Publisher Copyright:
© 2018 Technical Committee on Control Theory, Chinese Association of Automation.
PY - 2018/10/5
Y1 - 2018/10/5
N2 - 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.
AB - 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.
KW - Actor-critic neural network
KW - Adaptive dynamic programming
KW - Multi-agent systems
KW - Optimal tracking control
UR - http://www.scopus.com/inward/record.url?scp=85056134502&partnerID=8YFLogxK
U2 - 10.23919/ChiCC.2018.8483268
DO - 10.23919/ChiCC.2018.8483268
M3 - Conference contribution
AN - SCOPUS:85056134502
T3 - Chinese Control Conference, CCC
SP - 7037
EP - 7042
BT - Proceedings of the 37th Chinese Control Conference, CCC 2018
A2 - Chen, Xin
A2 - Zhao, Qianchuan
PB - IEEE Computer Society
T2 - 37th Chinese Control Conference, CCC 2018
Y2 - 25 July 2018 through 27 July 2018
ER -