Output regulation of unknown linear systems using average cost reinforcement learning

DOI10.1016/J.AUTOMATICA.2019.108549zbMATH Open1429.93153OpenAlexW2974120149WikidataQ127233182 ScholiaQ127233182MaRDI QIDQ2280965FDOQ2280965

Authors Farnaz Adib Yaghmaie, Svante Gunnarsson, Frank L. Lewis 

Publication date 19 December 2019

Published in Automatica (Search for Journal in Brave)

Full work available at URL http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-162304

zbMATH Keywords

linear systemsoptimal controloutput regulationreinforcement learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Existence theories for optimal control problems involving ordinary differential equations (49J15) Linear systems in control theory (93C05) Control/observation systems governed by ordinary differential equations (93C15)

Recommendations

• Output‐feedback H_∞ quadratic tracking control of linear systems using reinforcement learning
• Linear quadratic tracking control of unknown systems: a two-phase reinforcement learning method
• Adaptive optimal output tracking of continuous-time systems via output-feedback-based reinforcement learning
• Undiscounted reinforcement learning for infinite-time optimal output tracking and disturbance rejection of discrete-time LTI systems with unknown dynamics
• Optimal output regulation for unknown continuous-time linear systems by internal model and adaptive dynamic programming

Cites Work

• scientific article; zbMATH DE number 47926 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• Adaptation and regulation with signal detection implies internal model
• Adaptive Dynamic Programming and Adaptive Optimal Output Regulation of Linear Systems
• An optimal PID controller design for nonlinear constrained optimal control problems
• Approximate optimal trajectory tracking for continuous-time nonlinear systems
• Approximate solutions to the time-invariant Hamilton-Jacobi-Bellman equation
• Bipartite and cooperative output synchronizations of linear heterogeneous agents: a unified framework
• Dynamic programming and stochastic control processes
• Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning
• Multiparty Consensus of Linear Heterogeneous Multiagent Systems
• Optimal tracking control of nonlinear partially-unknown constrained-input systems using integral reinforcement learning
• Output regulation of linear heterogeneous multi-agent systems via output and state feedback
• Reinforcement learning for a class of continuous-time input constrained optimal control problems
• Reinforcement learning. An introduction
• The zero dynamics of a nonlinear system: from the origin to the latest progresses of a long successful story

Cited In (8)

• Adaptive optimal output tracking of continuous-time systems via output-feedback-based reinforcement learning
• Optimal output regulation for unknown continuous-time linear systems by internal model and adaptive dynamic programming
• Fixed‐time output regulation of linear delay systems by smooth time‐varying control
• Model-free learning-based distributed cooperative tracking control of human-in-the-loop multi-agent systems
• Reinforcement learning‐based robust optimal output regulation for constrained nonlinear systems with static and dynamic uncertainties
• Incremental reinforcement learning and optimal output regulation under unmeasurable disturbances
• Convergence results for an averaged LQR problem with applications to reinforcement learning
• Optimal robust formation control for heterogeneous multi‐agent systems based on reinforcement learning

This page was built for publication: Output regulation of unknown linear systems using average cost reinforcement learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2280965)