A data-ensemble-based approach for sample-efficient LQ control of linear time-varying systems

DOI10.1016/J.JFRANKLIN.2025.108118MaRDI QIDQ6834300zbMATH OpenFDO

Authors Sahel Vahedi Noori, Maryam Babazadeh

Publication date 31 March 2026

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JFRANKLIN.2025.108118

zbMATH Keywords

convex optimizationKKT conditionslinear quadratic (LQ) controldata-driven controlfinite-horizon

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Discrete-time control/observation systems (93C55)

Cites work

• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• A class of subspace model identification algorithms to identify periodically and arbitrarily time-varying systems
• A note on persistency of excitation
• Adaptive dynamic programming for finite-horizon optimal control of linear time-varying discrete-time systems
• An Iterative Data-Driven Linear Quadratic Method to Solve Nonlinear Discrete-Time Tracking Problems
• An efficient LQR design for discrete-time linear periodic system based on a novel lifting method
• Batch-to-Batch Finite-Horizon LQ Control for Unknown Discrete-Time Linear Systems Via Stochastic Extremum Seeking
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• Data Informativity: A New Perspective on Data-Driven Analysis and Control
• Data-driven control based on the behavioral approach: from theory to applications in power systems
• Direct Data-Driven Control of Linear Time-Varying Systems
• Dual-loop iterative optimal control for the finite horizon LQR problem with unknown dynamics
• Extremum seeking for optimal control problems with unknown time-varying systems and unknown objective functions
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• Low-complexity learning of linear quadratic regulators from noisy data
• Model-free LQR design by Q-function learning
• Model-free design of stochastic LQR controller from a primal-dual optimization perspective
• Primal-Dual Q-Learning Framework for LQR Design
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems

This page was built for publication: A data-ensemble-based approach for sample-efficient LQ control of linear time-varying systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6834300)