Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems

Abstract

Optimal control of nonlinear systems is a difficult problem which has been addressed by both the Control Theory (CT) and Reinforcement Learning (RL) communities. Frequently, the former relies on the linearization of the system thus obtaining only local guarantees. The latter relies on data to build model-free controllers, focused solely on performances. In this paper we propose a methodology to combine the advantages of both approaches, casting the formulation of an optimal local Linear Quadratic Regulator (LQR) into a Deep RL problem. Our solution builds on the linear framework to derive a learnt nonlinear controller showing local stability properties and global performances.
Fichier principal
Vignette du fichier
CDC_2021_final_version.pdf (453.39 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03353584 , version 1 (24-09-2021)

Identifiers

Cite

Samuele Zoboli, Vincent Andrieu, Daniele Astolfi, Giacomo Casadei, Jilles S Dibangoye, et al.. Reinforcement Learning Policies With Local LQR Guarantees For Nonlinear Discrete-Time Systems. CDC, Dec 2021, Texas, United States. ⟨10.1109/CDC45484.2021.9683721⟩. ⟨hal-03353584⟩
349 View
624 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More