Neural H2 Control Using Continuous-Time Reinforcement Learning

In this article, we discuss continuous-time H-2 control for the unknown nonlinear system. We use differential neural networks to model the system, then apply the H-2 tracking control based on the neural model. Since the neural H-2 control is very sensitive to the neural modeling error, we use reinforcement learning to improve the control performance. The stabilities of the neural modeling and the H-2 tracking control are proven. The convergence of the approach is also given. The proposed method is validated with two benchmark control problems.

Automated summary

This article discusses the application of continuous-time H-2 control in unknown nonlinear systems. We use differential neural networks to model the system and apply H-2 tracking control based on the neural model. Due to the sensitivity of neural H-2 control to neural modeling errors, we use reinforcement learning to improve control performance. The stability of neural modeling and H-2 tracking control is proven, and the convergence of the approach is also given. The proposed method is validated with two benchmark control problems.