Learning Control for LQR with Unknown Packet Loss Rate Using Finite Channel Samples

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Zhenning, Xu, Liang, Mo, Yilin, Wang, Xiaofan
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913893181292544
author Zhang, Zhenning
Xu, Liang
Mo, Yilin
Wang, Xiaofan
author_facet Zhang, Zhenning
Xu, Liang
Mo, Yilin
Wang, Xiaofan
contents This paper studies the linear quadratic regulator (LQR) problem over an unknown Bernoulli packet loss channel. The unknown loss rate is estimated using finite channel samples and a certainty-equivalence (CE) optimal controller is then designed by treating the estimate as the true rate. The stabilizing capability and sub-optimality of the CE controller critically depend on the estimation error of loss rate. For discrete-time linear systems, we provide a stability threshold for the estimation error to ensure closed-loop stability, and analytically quantify the sub-optimality in terms of the estimation error and the difference in modified Riccati equations. Next, we derive the upper bound on sample complexity for the CE controller to be stabilizing. Tailored results with less conservatism are delivered for scalar systems and n-dimensional systems with invertible input matrix. Moreover, we establish a sufficient condition, independent of the unknown loss rate, to verify whether the CE controller is stabilizing in a probabilistic sense. Finally, numerical examples are used to validate our results.
format Preprint
id arxiv_https___arxiv_org_abs_2501_02899
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Control for LQR with Unknown Packet Loss Rate Using Finite Channel Samples
Zhang, Zhenning
Xu, Liang
Mo, Yilin
Wang, Xiaofan
Systems and Control
This paper studies the linear quadratic regulator (LQR) problem over an unknown Bernoulli packet loss channel. The unknown loss rate is estimated using finite channel samples and a certainty-equivalence (CE) optimal controller is then designed by treating the estimate as the true rate. The stabilizing capability and sub-optimality of the CE controller critically depend on the estimation error of loss rate. For discrete-time linear systems, we provide a stability threshold for the estimation error to ensure closed-loop stability, and analytically quantify the sub-optimality in terms of the estimation error and the difference in modified Riccati equations. Next, we derive the upper bound on sample complexity for the CE controller to be stabilizing. Tailored results with less conservatism are delivered for scalar systems and n-dimensional systems with invertible input matrix. Moreover, we establish a sufficient condition, independent of the unknown loss rate, to verify whether the CE controller is stabilizing in a probabilistic sense. Finally, numerical examples are used to validate our results.
title Learning Control for LQR with Unknown Packet Loss Rate Using Finite Channel Samples
topic Systems and Control
url https://arxiv.org/abs/2501.02899