Model-Free Reinforcement Learning by Embedding an Auxiliary System for Optimal Control of Nonlinear Systems

In this article, a novel integral reinforcement learning (IRL) algorithm is proposed to solve the optimal control problem for continuous-time nonlinear systems with unknown dynamics. The main challenging issue in learning is how to reject the oscillation caused by the externally added probing noise....

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2022-04, Vol.33 (4), p.1520-1534
Hauptverfasser:	Xu, Zhenhui, Shen, Tielong, Cheng, Daizhan
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Approximate optimal control design Artificial neural networks auxiliary trajectory completely model-free Control systems Convergence Dynamical systems Embedding Feedback control Heuristic algorithms integral reinforcement learning (IRL) Iterative methods Learning Machine learning Mathematical model Neural networks Nonlinear control Nonlinear systems Optimal control Reinforcement System dynamics Trajectory Trajectory control
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!