Noise Sensitivity of the Semidefinite Programs for Direct Data-Driven LQR
Preprint
Abstract
In this paper, we study the noise sensitivity of the semidefinite program (SDP) proposed for direct data-driven infinite-horizon linear quadratic regulator (LQR) problem for discrete-time linear time-invariant systems. While this SDP is shown to find the true LQR controller in the noise-free setting, we show that it leads to a trivial solution with zero gain matrices when data is corrupted by noise, even when the noise is arbitrarily small. We then study a variant of the SDP that includes a robustness promoting regularization term and prove that regularization does not fully eliminate the sensitivity issue. In particular, the solution of the regularized SDP converges in probability also to a trivial solution.Keywords
All Related Versions
This publication has 13 references indexed in Scilit:
- On the Equivalence of Direct and Indirect Data-Driven Predictive Control ApproachesIEEE Control Systems Letters, 2024
- Guarantees for data-driven control of nonlinear systems using semidefinite programming: A surveyAnnual Reviews in Control, 2023
- Data-driven quadratic stabilization and LQR control of LTI systemsAutomatica, 2023
- A Quantitative Notion of Persistency of Excitation and the Robust Fundamental LemmaIEEE Control Systems Letters, 2022
- Low-complexity learning of Linear Quadratic Regulators from noisy dataAutomatica, 2021
- From Noisy Data to Feedback Controllers: Nonconservative Design via a Matrix S-LemmaIEEE Transactions on Automatic Control, 2020
- Willems’ Fundamental Lemma for State-Space Systems and Its Extension to Multiple DatasetsIEEE Control Systems Letters, 2020
- Formulas for Data-Driven Control: Stabilization, Optimality, and RobustnessIEEE Transactions on Automatic Control, 2019
- On the Sample Complexity of the Linear Quadratic RegulatorFoundations of Computational Mathematics, 2019
- A note on persistency of excitationSystems & Control Letters, 2005