Event-Triggered Multigradient Recursive Reinforcement Learning Tracking Control for Multiagent Systems

In this article, the tracking control problem of event-triggered multigradient recursive reinforcement learning is investigated for nonlinear multiagent systems (MASs). Attention is focused on the distributed reinforcement learning approach for MASs. The critic neural network (NN) is applied to estimate the long-term strategic utility function, and the actor NN is designed to approximate the uncertain dynamics in MASs. The multigradient recursive (MGR) strategy is tailored to learn the weight vector in NN, which eliminates the local optimal problem inherent in gradient descent method and decreases the dependence of initial value. Furthermore, reinforcement learning and event-triggered mechanism can improve the energy conservation of MASs by decreasing the amplitude of the controller signal and the controller update frequency, respectively. It is proved that all signals in MASs are semiglobal uniformly ultimately bounded (SGUUB) according to the Lyapunov theory. Simulation results are given to demonstrate the effectiveness of the proposed strategy.

Automated summary

This article investigates the tracking control problem of event-triggered multigradient recursive reinforcement learning for nonlinear multiagent systems. It focuses on the distributed reinforcement learning approach, using a critic neural network to estimate the long-term strategic utility function and an actor neural network to approximate uncertain dynamics. The multigradient recursive strategy is used to learn the weight vector in the neural network, eliminating local optimal problems and reducing dependence on initial values. Furthermore, reinforcement learning and event-triggered mechanism improve energy conservation of multiagent systems.