Model-free \(H_{\infty }\) control design for unknown linear discrete-time systems via Q-learning with LMI

DOI10.1016/j.automatica.2010.05.002zbMath1205.93046OpenAlexW1488674906MaRDI QIDQ608439

Sumit K. Garg

Publication date: 25 November 2010

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2010.05.002

zbMATH Keywords

LMIQ-learning\(H_{\infty }\) controllinear discrete-time systemmodel-free

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Design techniques (robust design, computer-aided design, etc.) (93B51) Discrete-time control/observation systems (93C55) (H^infty)-control (93B36) Linear systems in control theory (93C05)

Related Items (11)

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 ⋮ Model-free finite-horizon optimal control of discrete-time two-player zero-sum games ⋮ Data-driven designs of observers and controllers via solving model matching problems ⋮ Data-based \(\mathcal{L}_2\) gain optimal control for discrete-time system with unknown dynamics ⋮ Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning ⋮ From model-based control to data-driven control: survey, classification and perspective ⋮ Data-driven approximate Q-learning stabilization with optimality error bound analysis ⋮ Model-FreeH_∞Control Design for Unknown Continuous-Time Linear System Using Adaptive Dynamic Programming ⋮ Discrete-time ℋ_∞control for nonlinear polynomial systems ⋮ Computational intelligence in uncertainty quantification for learning control and differential games

Cites Work

• Model-free \(Q\)-learning designs for linear discrete-time zero-sum games with application to \(H^\infty\) control
• Galerkin approximations of the generalized Hamilton-Jacobi-Bellman equation
• An Approximation Theory of Optimal Control for Trainable Manipulators
• Linear Matrix Inequalities in System and Control Theory
• Approximate Dynamic Programming
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Model-free \(H_{\infty }\) control design for unknown linear discrete-time systems via Q-learning with LMI