Regularization for Covariance Parameterization of Direct Data-Driven LQR Control

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Feiran, Chiuso, Alessandro, Dörfler, Florian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910859133976576
author Zhao, Feiran
Chiuso, Alessandro
Dörfler, Florian
author_facet Zhao, Feiran
Chiuso, Alessandro
Dörfler, Florian
contents As the benchmark of data-driven control methods, the linear quadratic regulator (LQR) problem has gained significant attention. A growing trend is direct LQR design, which finds the optimal LQR gain directly from raw data and bypassing system identification. To achieve this, our previous work develops a direct LQR formulation parameterized by sample covariance. In this paper, we propose a regularization method for the covariance-parameterized LQR. We show that the regularizer accounts for the uncertainty in both the steady-state covariance matrix corresponding to closed-loop stability, and the LQR cost function corresponding to averaged control performance. With a positive or negative coefficient, the regularizer can be interpreted as promoting either exploitation or exploration, which are well-known trade-offs in reinforcement learning. In simulations, we observe that our covariance-parameterized LQR with regularization can significantly outperform the certainty-equivalence LQR in terms of both the optimality gap and the robust closed-loop stability.
format Preprint
id arxiv_https___arxiv_org_abs_2503_02985
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Regularization for Covariance Parameterization of Direct Data-Driven LQR Control
Zhao, Feiran
Chiuso, Alessandro
Dörfler, Florian
Systems and Control
Optimization and Control
As the benchmark of data-driven control methods, the linear quadratic regulator (LQR) problem has gained significant attention. A growing trend is direct LQR design, which finds the optimal LQR gain directly from raw data and bypassing system identification. To achieve this, our previous work develops a direct LQR formulation parameterized by sample covariance. In this paper, we propose a regularization method for the covariance-parameterized LQR. We show that the regularizer accounts for the uncertainty in both the steady-state covariance matrix corresponding to closed-loop stability, and the LQR cost function corresponding to averaged control performance. With a positive or negative coefficient, the regularizer can be interpreted as promoting either exploitation or exploration, which are well-known trade-offs in reinforcement learning. In simulations, we observe that our covariance-parameterized LQR with regularization can significantly outperform the certainty-equivalence LQR in terms of both the optimality gap and the robust closed-loop stability.
title Regularization for Covariance Parameterization of Direct Data-Driven LQR Control
topic Systems and Control
Optimization and Control
url https://arxiv.org/abs/2503.02985