Discrete-Time H2 Neural Control Using Reinforcement Learning

In this article, we discuss H-2 control for unknown nonlinear systems in discrete time. A discrete-time recurrent neural network is used to model the nonlinear system, and then, the H-2 tracking control is applied based on the neural model. Since this neural H-2 control is very sensitive to the neural modeling error, we use reinforcement learning and another neural approximator to improve tracking accuracy and robustness of the controller. The stabilities of the neural identifier and the H-2 tracking control are proven. The convergence of the approach is also given. The proposed method is validated with the control of the pan and tilt robot and the surge tank.

Automated summary

This article discusses the H-2 control approach for unknown nonlinear systems in discrete time using a discrete-time recurrent neural network to model the system and applying H-2 tracking control based on the neural model. To improve tracking accuracy and robustness, reinforcement learning and another neural approximator are utilized. The stability of the neural identifier and the H-2 tracking control are proven, and the convergence of the approach is demonstrated through control of pan and tilt robots and surge tanks.