Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method

DOI10.1016/j.automatica.2022.110761OpenAlexW4310258352MaRDI QIDQ2682307

Yanyan Li

Publication date: 31 January 2023

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2022.110761

zbMATH Keywords

reinforcement learningsingular perturbation theorylinear quadratic tracking controldiscounted cost function

Mathematics Subject Classification ID

Linear systems in control theory (93C05) Time-scale analysis and singular perturbations in control/observation systems (93C70) Linear-quadratic optimal control problems (49N10)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Output-feedback adaptive optimal control of interconnected systems based on robust adaptive dynamic programming
• Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning
• Model-free event-triggered control algorithm for continuous-time linear systems with optimal performance
• Stabilization with discounted optimal control
• Non-zero sum Nash Q-learning for unknown deterministic continuous-time linear systems
• Resilient reinforcement learning and robust output regulation under denial-of-service attacks
• Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems
• New insight into the simultaneous policy update algorithms related to \(H_\infty\) state feedback control
• Approximate optimal trajectory tracking for continuous-time nonlinear systems
• Optimal control for a new class of singularly perturbed linear systems
• Simultaneous policy update algorithms for learning the solution of linear continuous-time \(H_{\infty}\) state feedback control
• Reduced-dimensional reinforcement learning control using singular perturbation approximations
• Adaptive Dynamic Programming and Adaptive Optimal Output Regulation of Linear Systems
• Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning
• Leader-to-Formation Stability of Multiagent Systems: An Adaptive Optimal Control Approach
• Cooperative Q-Learning for Rejection of Persistent Adversarial Inputs in Networked Linear Quadratic Systems
• Infinite horizon linear quadratic tracking problem: A discounted cost function approach
• Robust Adaptive Dynamic Programming
• Adaptive composite suboptimal control for linear singularly perturbed systems with unknown slow dynamics
• A Distributed Indirect Adaptive Approach to Cooperative Tracking in Networks of Uncertain Single-Input Single-Output Systems
• Self-Learning Optimal Regulation for Discrete-Time Nonlinear Systems Under Event-Driven Formulation
• Reinforcement Learning-Based Adaptive Optimal Exponential Tracking Control of Linear Systems With Unknown Dynamics
• Stability Analysis of Discrete-Time Infinite-Horizon Optimal Control With Discounted Cost
• Algorithm 432 [C2: Solution of the matrix equation AX + XB = C [F4]]
• Finite-Horizon Discounted Optimal Control: Stability and Performance

This page was built for publication: Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method