Zero-sum game-based optimal control for discrete-time Markov jump systems: a parallel off-policy Q-learning method

DOI10.1016/J.AMC.2023.128462MaRDI QIDQ6130156FDOQ6130156

Authors:

Publication date: 18 April 2024

Published in: Applied Mathematics and Computation (Search for Journal in Brave)

Recommendations

• \(\mathcal{H}_\infty\) tracking learning control for discrete-time Markov jump systems: a parallel off-policy reinforcement learning
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• \(Q\)-learning-based non-zero sum games for Markov jump multiplayer systems under actor-critic NNs structure
• Off-policy based adaptive dynamic programming method for nonzero-sum games on discrete-time system

zbMATH Keywords

optimal controlMarkov jump systems\(Q\)-learning methodgame-coupled algebraic Riccati equation

Mathematics Subject Classification ID

Model systems in control theory (93Cxx) Stochastic systems and control (93Exx) Controllability, observability, and system structure (93Bxx)

Cited In (3)

• Finite-horizon Q-learning for discrete-time zero-sum games with application to \(H_{\infty}\) control
• \(Q\)-learning-based non-zero sum games for Markov jump multiplayer systems under actor-critic NNs structure
• Successive over relaxation for model-free LQR control of discrete-time Markov jump systems

This page was built for publication: Zero-sum game-based optimal control for discrete-time Markov jump systems: a parallel off-policy \(Q\)-learning method

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6130156)