Output feedback Q-learning for discrete-time linear zero-sum games with application to the \(H_\infty\) control

DOI10.1016/J.AUTOMATICA.2018.05.027zbMath1402.93126OpenAlexW2807176303MaRDI QIDQ1626885

Syed Ali Asad Rizvi, Zongli Lin

Publication date: 21 November 2018

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2018.05.027

zbMATH Keywords

ADP\(H_\infty\) controlzero-sum gamesoutput feedbackreinforcement learningQ-learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Feedback control (93B52) 2-person games (91A05) Application models in control theory (93C95) Discrete-time control/observation systems (93C55) (H^infty)-control (93B36) Linear systems in control theory (93C05)

Related Items (16)

H_∞ optimal control of unknown linear systems by adaptive dynamic programming with applications to time‐delay systems ⋮ Improved model-free H∞ control for batch processes via off-policy 2D game Q-learning ⋮ Output‐feedback Q‐learning for discrete‐time linear H^∞ tracking control: A Stackelberg game approach ⋮ Optimal game theoretic solution of the pursuit‐evasion intercept problem using on‐policy reinforcement learning ⋮ Model-free finite-horizon optimal control of discrete-time two-player zero-sum games ⋮ Reinforcement learning and cooperative \(H_\infty\) output regulation of linear continuous-time multi-agent systems ⋮ Undiscounted reinforcement learning for infinite-time optimal output tracking and disturbance rejection of discrete-time LTI systems with unknown dynamics ⋮ Safe adaptive learning algorithm with neural network implementation for H∞ control of nonlinear safety‐critical system ⋮ Incremental reinforcement learning and optimal output regulation under unmeasurable disturbances ⋮ Robust H_∞ tracking of linear <scp>discrete‐time</scp> systems using <scp>Q‐learning</scp> ⋮ \(\mathcal{H}_\infty\) tracking learning control for discrete-time Markov jump systems: a parallel off-policy reinforcement learning ⋮ Output feedback adaptive dynamic programming for linear differential zero-sum games ⋮ Experience replay–based output feedback Q‐learning scheme for optimal output tracking control of discrete‐time linear systems ⋮ Q-learning-based target selection for bearings-only autonomous navigation ⋮ Model-free \(H_\infty\) tracking control for de-oiling hydrocyclone systems via off-policy reinforcement learning ⋮ Model-free optimal control of discrete-time systems with additive and multiplicative noises

Cites Work

• Unnamed Item
• \(\mathrm{H}_\infty\) control of linear discrete-time systems: off-policy reinforcement learning
• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• \({\mathcal Q}\)-learning
• Neural-network-observer-based optimal control for unknown nonlinear systems using adaptive dynamic programming
• Adaptive dynamic programming for online solution of a zero-sum differential game
• Stability Analysis of Discrete-Time Infinite-Horizon Optimal Control With Discounted Cost

This page was built for publication: Output feedback Q-learning for discrete-time linear zero-sum games with application to the \(H_\infty\) control