Stability Analysis of Optimal Adaptive Control Using Value Iteration With Approximation Errors
Author:
- 5 January 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automatic Control
- Vol. 63 (9) , 3119-3126
Abstract
Adaptive optimal control using value iteration initiated from a stabilizing control policy is theoretically analyzed in terms of stability of the system during the learning stage without ignoring the effects of approximation errors. This analysis includes the system operated using any single/constant resulting control policy and also using an evolving/time-varying control policy. A feature of the presented results is providing estimations of the region of attraction so that if the initial condition is within the region, the whole trajectory will remain inside it and hence, the function approximation results remain valid.Keywords
All Related Versions
Funding Information
- National Science Foundation (1509778)
This publication has 12 references indexed in Scilit:
- Model-Free Optimal Tracking Control via Critic-Only Q-LearningIEEE Transactions on Neural Networks and Learning Systems, 2016
- Value and Policy Iterations in Optimal Control and Adaptive Dynamic ProgrammingIEEE Transactions on Neural Networks and Learning Systems, 2015
- Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear SystemsIEEE Transactions on Cybernetics, 2015
- Convergence Proof of Approximate Policy Iteration for Undiscounted Optimal Control of Discrete-Time SystemsCognitive Computation, 2015
- Revisiting Approximate Dynamic Programming and its ConvergenceIEEE Transactions on Cybernetics, 2014
- Finite-Approximation-Error-Based Optimal Control Approach for Discrete-Time Nonlinear SystemsIEEE Transactions on Cybernetics, 2013
- Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence ProofIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2008
- Relaxing Dynamic ProgrammingIEEE Transactions on Automatic Control, 2006
- An upper bound on the loss from approximate optimal-value functionsMachine Learning, 1994
- Multilayer feedforward networks are universal approximatorsNeural Networks, 1989