Discrete-Time H<sub>2</sub> Neural Control Using Reinforcement Learning.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 33017294.
- Also identified by DOI 10.1109/TNNLS.2020.3026010.
- No licence information is recorded for this record.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
In this article, we discuss H<sub>2</sub> 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<sub>2</sub> tracking control is applied based on the neural model. Since this neural H<sub>2</sub> 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<sub>2</sub> 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.
Medical subject headings
- Neural Networks, Computer
- Nonlinear Dynamics
- Reinforcement, Psychology