Online identification and control of PDEs via reinforcement learning methods

DOI10.1007/s10444-024-10167-yzbMath1547.65165MaRDI QIDQ6607032

Michele Palladino, Andrea Pesare, Agnese Pacifico, Alessandro Alla

Publication date: 17 September 2024

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

zbMATH Keywords

system identificationnumerical approximationreinforcement learningBayesian linear regressionstabilization of PDEsstate-dependent Riccati equations

Mathematics Subject Classification ID

Computational learning theory (68Q32) Bayesian inference (62F15) Learning and adaptive systems in artificial intelligence (68T05) Optimal feedback synthesis (49N35) Stability in context of PDEs (35B35) System identification (93B30) Nonlinear ordinary differential equations and systems (34A34) Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65M99)

This page was built for publication: Online identification and control of PDEs via reinforcement learning methods