Reinforcement learning-based optimal control for Markov jump systems with completely unknown dynamics

DOI10.1016/j.automatica.2024.111886MaRDI QIDQ6659172

Xiongtao Shi, Chenglong Du, Yan-Jie Li, Guangdeng Zong, Weihua Gui, Chao-Yang Chen

Publication date: 8 January 2025

Published in: Automatica (Search for Journal in Brave)

zbMATH Keywords

optimal controlreinforcement learningcoupled algebraic Riccati equationMarkov jump systemsparallel policy iteration

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Cites Work

• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• Disturbance attenuation and rejection for stochastic Markovian jump system with partially known transition probabilities
• Dissipative output feedback tracking control of Markov jump systems under compensation scheme
• Model-free optimal control of discrete-time systems with additive and multiplicative noises
• Online reinforcement learning multiplayer non-zero sum games of continuous-time Markov jump linear systems
• Finite-time asynchronous sliding mode control for Markovian jump systems
• A novel iterative algorithm for solving coupled Riccati equations
• The linear quadratic optimal control problem for discrete-time Markov jump linear singular systems
• Linear Quadratic Tracking Control of Partially-Unknown Continuous-Time Systems Using Reinforcement Learning
• Controllability, stabilizability, and continuous-time Markovian jump linear quadratic control
• Numerical solution of the state dependent noise problem
• A Descriptor System Approach to Stability and Stabilization of Discrete-Time Switched PWA Systems
• Lyapunov iterations for optimal control of jump linear systems at steady state
• An Improved Homogeneous Polynomial Approach for Adaptive Sliding-Mode Control of Markov Jump Systems With Actuator Faults
• Adaptive Tracking Control of Hybrid Switching Markovian Systems with Its Applications
• Reinforcement learning‐based adaptive optimal tracking algorithm for Markov jump systems with partial unknown dynamics
• An Inversion-Free Iterative Algorithm for Riccati Matrix Equations in Discrete-Time Markov Jump Systems
• Dissipativity-based finite-time asynchronous output feedback control for wind turbine system via a hidden Markov model
• Self-triggered finite-time control for discrete-time Markov jump systems
• Probabilistic Event-Triggered Policy for Extended Dissipative Finite-Time Control of MJSs under Cyber-Attacks and Actuator Failures

This page was built for publication: Reinforcement learning-based optimal control for Markov jump systems with completely unknown dynamics