Saved in:
Bibliographic Details
Main Authors: Li, Weijian, Malikopoulos, Andreas A.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.22267
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909870044741632
author Li, Weijian
Malikopoulos, Andreas A.
author_facet Li, Weijian
Malikopoulos, Andreas A.
contents In this paper, we investigate the infinite-horizon risk-constrained linear quadratic regulator problem (RC-QR), which augments the classical LQR formulation with a statistical constraint on the variability of the system state to incorporate risk awareness, a key requirement in safety-critical control applications. We propose an actor-critic learning algorithm that jointly performs policy evaluation and policy improvement in a model-free and online manner. The RC-QR problem is first reformulated as a max-min optimization problem, from which we develop a multi-time-scale stochastic approximation scheme. The critic employs temporal-difference learning to estimate the action-value function, the actor updates the policy parameters via a policy gradient step, and the dual variable is adapted through gradient ascent to enforce the risk constraint.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22267
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Actor-Critic Learning for Risk-Constrained Linear Quadratic Regulation
Li, Weijian
Malikopoulos, Andreas A.
Optimization and Control
In this paper, we investigate the infinite-horizon risk-constrained linear quadratic regulator problem (RC-QR), which augments the classical LQR formulation with a statistical constraint on the variability of the system state to incorporate risk awareness, a key requirement in safety-critical control applications. We propose an actor-critic learning algorithm that jointly performs policy evaluation and policy improvement in a model-free and online manner. The RC-QR problem is first reformulated as a max-min optimization problem, from which we develop a multi-time-scale stochastic approximation scheme. The critic employs temporal-difference learning to estimate the action-value function, the actor updates the policy parameters via a policy gradient step, and the dual variable is adapted through gradient ascent to enforce the risk constraint.
title Actor-Critic Learning for Risk-Constrained Linear Quadratic Regulation
topic Optimization and Control
url https://arxiv.org/abs/2510.22267