A Lyapunov characterization of robust policy optimization

DOI10.1007/s11768-023-00163-wzbMath1530.93426OpenAlexW4386962717MaRDI QIDQ6061923

Zhong-Ping Jiang, Leilei Cui

Publication date: 30 November 2023

Published in: Control Theory and Technology (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11768-023-00163-w

zbMATH Keywords

Lyapunov's direct methodinput-to-state stability (ISS)policy optimizationpolicy iteration (PI)

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Input-output approaches in control theory (93D25)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Computational adaptive optimal control for continuous-time linear systems with completely unknown dynamics
• Human motor learning is robust to control-dependent noise
• Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems
• A note on persistency of excitation
• Adaptive Dynamic Programming and Adaptive Optimal Output Regulation of Linear Systems
• Global Adaptive Dynamic Programming for Continuous-Time Nonlinear Systems
• Comments on "A matrix inequality associated with bounds on solutions of algebraic Riccati and Lyapunov equation" by J.M. Saniuk and I.B. Rhodes
• Robust Policy Iteration for Continuous-Time Linear Quadratic Regulation
• Convergence and Sample Complexity of Gradient Methods for the Model-Free Linear–Quadratic Regulator Problem
• Sensitivity of the stable discrete-time Lyapunov equation
• Reinforcement Learning for Adaptive Optimal Stationary Control of Linear Stochastic Systems

This page was built for publication: A Lyapunov characterization of robust policy optimization