Abstract:
Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence gua...Show MoreMetadata
Abstract:
Model-free learning-based control methods have seen great success recently. However, such methods typically suffer from poor sample complexity and limited convergence guarantees. This is in sharp contrast to classical model-based control, which has a rich theory but typically requires strong modeling assumptions. In this paper, we combine the two approaches. We consider a dynamical system with both linear and non-linear components and use the linear model to define a warm start for a model-free, policy gradient method. We show this hybrid approach outperforms the model-based controller while avoiding the convergence issues associated with model-free approaches via both numerical experiments and theoretical analyses, in which we derive sufficient conditions on the non-linear component such that our approach is guaranteed to converge to the (nearly) global optimal controller.
Published in: 2021 60th IEEE Conference on Decision and Control (CDC)
Date of Conference: 14-17 December 2021
Date Added to IEEE Xplore: 01 February 2022
ISBN Information: