Convergence of the Value Function in Optimal Control Problems with Unknown Dynamics
Andrea Pesare, Michele Palladino, Maurizio Falcone · 2021 European Control Conference (ECC) · 2021
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.