Title :
Convergence analysis for an identifier-based adaptive dynamic programming algorithm
Author :
Jun, Song ; Yugang, Niu ; Yuanyuan, Zou
Author_Institution :
Key Laboratory of Advanced Control and Optimization for Chemical Process (East China University of Science and Technology), Ministry of Education, Shanghai 200237, China
Abstract :
This paper investigates the uniformly ultimate boundedness (UUB) of an identifier-based adaptive dynamic programming (ADP) algorithm proposed in [7]. It is demonstrated that the estimation errors of weights in both critic and action networks are UUB during iteration learning. Moreover, a selection method on learning rates is also given.
Keywords :
Algorithm design and analysis; Artificial neural networks; Convergence; Estimation error; Heuristic algorithms; Markov processes; Optimal control; Adaptive Dynamic Programming (ADP); Markov Jump Systems (MJSs); Uniformly Ultimately Boundedness (UUB);
Conference_Titel :
Control Conference (CCC), 2015 34th Chinese
Conference_Location :
Hangzhou, China
DOI :
10.1109/ChiCC.2015.7260115
