Enregistré dans:
Détails bibliographiques
Auteurs principaux: Bandyopadhyay, Soutrik, Bhasin, Shubhendu
Format: Preprint
Publié: 2023
Sujets:
Accès en ligne:https://arxiv.org/abs/2304.13573
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909084128641024
author Bandyopadhyay, Soutrik
Bhasin, Shubhendu
author_facet Bandyopadhyay, Soutrik
Bhasin, Shubhendu
contents Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable safety guarantees, which restrict their applicability to real-time safety-critical systems. This paper proposes a safe Q-learning algorithm for partially unknown linear time-invariant systems to solve the linear quadratic regulator problem with user-defined state constraints. We frame the safe Q-learning problem as a constrained optimal control problem using reciprocal control barrier functions and show that such an extension provides a safety-assured control policy. To the best of our knowledge, Q-learning for continuous-time systems with state constraints has not yet been reported in the literature.
format Preprint
id arxiv_https___arxiv_org_abs_2304_13573
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Safe Q-learning for continuous-time linear systems
Bandyopadhyay, Soutrik
Bhasin, Shubhendu
Systems and Control
Q-learning is a promising method for solving optimal control problems for uncertain systems without the explicit need for system identification. However, approaches for continuous-time Q-learning have limited provable safety guarantees, which restrict their applicability to real-time safety-critical systems. This paper proposes a safe Q-learning algorithm for partially unknown linear time-invariant systems to solve the linear quadratic regulator problem with user-defined state constraints. We frame the safe Q-learning problem as a constrained optimal control problem using reciprocal control barrier functions and show that such an extension provides a safety-assured control policy. To the best of our knowledge, Q-learning for continuous-time systems with state constraints has not yet been reported in the literature.
title Safe Q-learning for continuous-time linear systems
topic Systems and Control
url https://arxiv.org/abs/2304.13573