Model-free linear quadratic regulator

DOI10.1007/978-3-030-60990-0_6MaRDI QIDQ2094032zbMATH OpenOpenAlexFDO

Authors Hesameddin Mohammadi, Mahdi Soltanolkotabi, Mihailo R. Jovanović

Publication date 28 October 2022

Full work available at URL https://doi.org/10.1007/978-3-030-60990-0_6

Mathematics Subject Classification ID

Linear-quadratic optimal control problems (49N10) Discrete-time control/observation systems (93C55) Stabilization of systems by feedback (93D15)

Recommendations

• On the sample complexity of the linear quadratic regulator
• Low-complexity learning of linear quadratic regulators from noisy data
• A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
• Convergence results for an averaged LQR problem with applications to reinforcement learning
• Model-free recursive LQ controller design(learning LQ control)

Cites work

• Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
• Derivative-free methods for policy optimization: guarantees for linear quadratic systems
• Hanson-Wright inequality and sub-Gaussian concentration
• High-dimensional probability. An introduction with applications in data science
• Optimal Rates for Zero-Order Convex Optimization: The Power of Two Function Evaluations

Cited in

(15)

• Low-complexity learning of linear quadratic regulators from noisy data
• Remarks on input to state stability of perturbed gradient flows, motivated by model-free feedback control learning
• Model-free design of stochastic LQR controller from a primal-dual optimization perspective
• On the sample complexity of the linear quadratic regulator
• Convergence results for an averaged LQR problem with applications to reinforcement learning
• On integral generalized policy iteration for continuous-time linear quadratic regulations
• Model-free recursive LQ controller design(learning LQ control)
• Derivative-free methods for policy optimization: guarantees for linear quadratic systems
• Policy Gradient Methods for the Noisy Linear Quadratic Regulator over a Finite Horizon
• Model-free control
• LQG online learning
• Analysis of the optimization landscape of Linear Quadratic Gaussian (LQG) control
• Policy gradient methods for discrete time linear quadratic regulator with random parameters
• Learning decentralized linear quadratic regulators with \(\sqrt{T}\) regret
• Accelerated optimization landscape of linear-quadratic regulator

This page was built for publication: Model-free linear quadratic regulator

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2094032)