Convergence of the Value Function in Optimal Control Problems with Unknown Dynamics
Optimization and Control
2021-05-31 v1
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.
Cite
@article{arxiv.2105.13708,
title = {Convergence of the Value Function in Optimal Control Problems with Unknown Dynamics},
author = {Andrea Pesare and Michele Palladino and Maurizio Falcone},
journal= {arXiv preprint arXiv:2105.13708},
year = {2021}
}
Comments
6 pages, 3 figures, accepted for the European Control Conference 2021