Stabilizing reinforcement learning control: a modular framework for optimizing over all stable behavior

DOI10.1016/j.automatica.2024.111642zbMath1537.93689MaRDI QIDQ6550241

Philip D. Loewen, Shuyuan Wang, R. Bhushan Gopaluni, Michael G. Forbes, Nathan P. Lawrence

Publication date: 5 June 2024

Published in: Automatica (Search for Journal in Brave)

zbMATH Keywords

stabilityneural networksreinforcement learningprocess controlYoula-Kučera parameterizationdata-driven control

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Feedback control (93B52) Stability of control systems (93D99)

This page was built for publication: Stabilizing reinforcement learning control: a modular framework for optimizing over all stable behavior