Stability-certified on-policy data-driven LQR via recursive learning and policy gradient

DOI10.1016/J.AUTOMATICA.2026.113101MaRDI QIDQ7304726zbMATH OpenFDO

Authors Lorenzo Sforni, Guido Carnevale, Ivano Notarnicola, Giuseppe Notarstefano

Publication date 28 July 2026

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2026.113101

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Feedback control (93B52) Networked control (93B70) Nonlinear systems in control theory (93C10)

Cites work

• \(\mathrm{H}_\infty\) control of linear discrete-time systems: off-policy reinforcement learning
• A Geometric Characterization of the Persistence of Excitation Condition for the Solutions of Autonomous Systems
• A note on persistency of excitation
• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Averaging analysis for discrete time and sampled data adaptive systems
• Bridging Direct and Indirect Data-Driven Control Formulations via Regularizations and Relaxations
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
• Data Informativity: A New Perspective on Data-Driven Analysis and Control
• Efficient Off-Policy Q-Learning for Data-Based Discrete-Time LQR Problems
• Exponential convergence of recursive last squares with exponential forgetting factor
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• From Noisy Data to Feedback Controllers: Nonconservative Design via a Matrix S-Lemma
• How and Why to Solve the Operator Equation AX −XB = Y
• Lectures in feedback design for multivariable systems
• Low-complexity learning of linear quadratic regulators from noisy data
• On the Certainty-Equivalence Approach to Direct Data-Driven LQR Design
• On the sample complexity of the linear quadratic regulator
• On Topological Properties of the Set of Stabilizing Feedback Gains
• Online learning of data-driven controllers for unknown switched linear systems
• Online optimal tracking control of continuous-time linear systems with unknown dynamics by using adaptive dynamic programming
• Persistency of excitation, sufficient richness and parameter convergence in discrete time adaptive control
• Robust Policy Iteration for Continuous-Time Linear Quadratic Regulation
• Stability and control of large-scale dynamical systems. A vector dissipative systems approach.
• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Value Iteration for Continuous-Time Linear Time-Invariant Systems

This page was built for publication: Stability-certified on-policy data-driven LQR via recursive learning and policy gradient

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7304726)