Discrete-time generalized policy iteration ADP algorithm with approximation errors
- 1 November 2017
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2017 IEEE Symposium Series on Computational Intelligence (SSCI)
Abstract
This paper concerns with a novel generalized policy iteration (GPI) algorithm with approximation errors. Approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The convergence of the developed algorithm is established to show that the iterative value function is convergent to a finite neighborhood of the optimal performance index function. Finally, numerical examples and comparisons are presented.Keywords
This publication has 12 references indexed in Scilit:
- Error-Tolerant Iterative Adaptive Dynamic Programming for Optimal Renewable Home Energy Scheduling and Battery ManagementIEEE Transactions on Industrial Electronics, 2017
- Mixed Iterative Adaptive Dynamic Programming for Optimal Battery Energy Control in Smart Residential MicrogridsIEEE Transactions on Industrial Electronics, 2017
- A novel policy iteration based deterministic Q-learning for discrete-time nonlinear systemsScience China Information Sciences, 2015
- Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear SystemsIEEE Transactions on Cybernetics, 2015
- Data-Driven Zero-Sum Neuro-Optimal Control for a Class of Continuous-Time Unknown Nonlinear Systems With Disturbance Using ADPIEEE Transactions on Neural Networks and Learning Systems, 2015
- Generalized Policy Iteration Adaptive Dynamic Programming for Discrete-Time Nonlinear SystemsIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015
- Infinite Horizon Self-Learning Optimal Control of Nonaffine Discrete-Time Nonlinear SystemsIEEE Transactions on Neural Networks and Learning Systems, 2015
- Discrete-Time Nonlinear HJB Solution Using Approximate Dynamic Programming: Convergence ProofIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2008
- Relaxed dynamic programming in switching systemsIEE Proceedings - Control Theory and Applications, 2006
- Relaxing Dynamic ProgrammingIEEE Transactions on Automatic Control, 2006