Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning

DOI10.1016/J.INS.2022.03.004MaRDI QIDQ6199564zbMATH OpenOpenAlexFDO

Authors Adolfo Perrusquía

Publication date 28 February 2024

Published in Information Sciences (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1016/j.ins.2022.03.004

zbMATH Keywords

output feedbackQ-learninggradient descentlinear quadratic regulatorpersistency of excitationstate observer parametrization

Mathematics Subject Classification ID

Feedback control (93B52) Linear systems in control theory (93C05) Lyapunov and other classical stabilities (Lagrange, Poisson, (L^p, l^p), etc.) in control theory (93D05) Observers (93B53)

Recommendations

• Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Reinforcement learning for linear exponential quadratic Gaussian problem
• Integral \(Q\)-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems
• Output‐feedback H_∞ quadratic tracking control of linear systems using reinforcement learning

Cites work

• Adaptive optimal control for continuous-time linear systems based on policy iteration
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• Continuous-time path planning for multi-agents with fuzzy reinforcement learning
• Continuous-time reinforcement learning for robust control under worst-case uncertainty
• Integral reinforcement learning and experience replay for adaptive optimal control of partially-unknown constrained-input continuous-time systems
• Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning
• Model-free \(H_{\infty }\) control design for unknown linear discrete-time systems via Q-learning with LMI
• Nonlinear systems.
• Online actor-critic algorithm to solve the continuous-time infinite horizon optimal control problem
• Optimal control
• Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
• Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
• Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
• Reinforcement learning solution for HJB equation arising in constrained optimal control problem
• Robust control under worst-case uncertainty for unknown nonlinear systems using modified reinforcement learning
• Sliding-mode observers
• \( \mathbb{Q} \)-learning algorithm in solving consensusability problem of discrete-time multi-agent systems

Cited in

(2)

• Explainable data-driven Q-learning control for a class of discrete-time linear autonomous systems
• Reinforcement learning for linear exponential quadratic Gaussian problem

This page was built for publication: Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6199564)