Stability Analysis of Optimal Adaptive Control using Value Iteration\n with Approximation Errors

2017/10/23 by Ali Heydari, Heydari, Ali · 1 citation
Engineering · #Advanced Control Systems Optimization #FOS: Computer and information sciences #FOS: Electrical engineering #FOS: Mathematics #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Optimization and Control (math.OC) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.1710.08530

openalex publication_date 2017/10/23 · openalex created_date 2022/10/02 · openalex updated_date 2026/07/28

Abstract

Adaptive optimal control using value iteration initiated from a stabilizing\ncontrol policy is theoretically analyzed in terms of stability of the system\nduring the learning stage without ignoring the effects of approximation errors.\nThis analysis includes the system operated using any single/constant resulting\ncontrol policy and also using an evolving/time-varying control policy. A\nfeature of the presented results is providing estimations of the \region\nof attraction so that if the initial condition is within the region, the whole\ntrajectory will remain inside it and hence, the function approximation results\nremain valid.\n

Cited by

• Lyapunov Function-guided Reinforcement Learning for Flight Control

Related

• Stabilizing Value Iteration with and without Approximation Errors
• Theoretical and Numerical Analysis of Approximate Dynamic Programming\n with Approximation Errors
• A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming
• Convergence of the Value Function in Optimal Control Problems with\n Unknown Dynamics
• Global Stability Notions to Enhance the Rigor and Robustness of Adaptive Control