Convergence of the Value Function in Optimal Control Problems with Unknown Dynamics

MaRDI QIDQ6368789zbMATH OpenFDO

Authors Andrea Pesare, Michele Palladino, M. Falcone

Publication date 28 May 2021

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37) Feedback control (93B52) Optimal stochastic control (93E20)

Abstract: We deal with the convergence of the value function of an approximate control problem with uncertain dynamics to the value function of a nonlinear optimal control problem. The assumptions on the dynamics and the costs are rather general and we assume to represent uncertainty in the dynamics by a probability distribution. The proposed framework aims to describe and motivate some model-based Reinforcement Learning algorithms where the model is probabilistic. We also show some numerical experiments which confirm the theoretical results.

This page was built for publication: Convergence of the Value Function in Optimal Control Problems with Unknown Dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6368789)