Adaptive dynamic programming for unknown continuous-time nonlinear systems via bias-policy iteration

DOI10.1016/J.AUTOMATICA.2026.112821MaRDI QIDQ6851049zbMATH OpenFDO

Authors Ruiqing Zhang, Huaiyuan Jiang, Bin Zhou

Publication date 27 February 2026

Published in Automatica (Search for Journal in Brave)

zbMATH Keywords

reinforcement learningpolicy iterationcontinuous-time nonlinear systemsunknown dynamicsinitial admissible control

Mathematics Subject Classification ID

Dynamic programming (90C39) Nonlinear systems in control theory (93C10) Adaptive control/observation systems (93C40)

This page was built for publication: Adaptive dynamic programming for unknown continuous-time nonlinear systems via bias-policy iteration

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6851049)