Adaptive Fault-Tolerant Tracking Control for Discrete-Time Multiagent Systems via Reinforcement Learning Algorithm

• Published in: IEEE transactions on cybernetics Vol. 51; no. 3; pp. 1163 - 1174
• Main Authors: Li, Hongyi, Wu, Ying, Chen, Mou
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Actuators; Adaptive algorithms; Adaptive control; Algorithms; Artificial neural networks; Control stability; Cost function; Discrete time systems; Discrete-time multiagent systems (MASs); Estimation; Fault tolerance; Fault tolerant systems; fault-tolerant control; Feedback control; Machine learning; Multi-agent systems; Multiagent systems; Neural networks; neural networks (NNs); Reinforcement learning; reinforcement learning algorithm; Tracking control
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2020.2982168

This article investigates the adaptive fault-tolerant tracking control problem for a class of discrete-time multiagent systems via a reinforcement learning algorithm. The action neural networks (NNs) are used to approximate unknown and desired control input signals, and the critic NNs are employed to estimate the cost function in the design procedure. Furthermore, the direct adaptive optimal controllers are designed by combining the backstepping technique with the reinforcement learning algorithm. Comparing the existing reinforcement learning algorithm, the computational burden can be effectively reduced by using the method of less learning parameters. The adaptive auxiliary signals are established to compensate for the influence of the dead zones and actuator faults on the control performance. Based on the Lyapunov stability theory, it is proved that all signals of the closed-loop system are semiglobally uniformly ultimately bounded. Finally, some simulation results are presented to illustrate the effectiveness of the proposed approach.