An iterative Q‐learning scheme for the global stabilization of discrete‐time linear systems subject to actuator saturation

DOI10.1002/RNC.4514zbMath1418.93223OpenAlexW2919343756WikidataQ128306947 ScholiaQ128306947MaRDI QIDQ5223457

Zongli Lin, Syed Ali Asad Rizvi

Publication date: 18 July 2019

Published in: International Journal of Robust and Nonlinear Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/rnc.4514

zbMATH Keywords

Riccati equationreinforcement learningactuator saturationconstrained controlQ-learning

Mathematics Subject Classification ID

Feedback control (93B52) Stabilization of systems by feedback (93D15) Discrete-time control/observation systems (93C55) Linear systems in control theory (93C05)

Related Items (4)

Input saturation: academic insights and future trends ⋮ H_∞ optimal control of unknown linear systems by adaptive dynamic programming with applications to time‐delay systems ⋮ Robust H_∞ tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp> ⋮ An iterative Q-learning based global consensus of discrete-time saturated multi-agent systems

This page was built for publication: An iterative Q‐learning scheme for the global stabilization of discrete‐time linear systems subject to actuator saturation