Learning of Neural Controllers by Random Search Technique

Victor WILLIAMS  Kiyotoshi MATSUOKA  

IEICE TRANSACTIONS on Information and Systems   Vol.E75-D   No.4   pp.595-601
Publication Date: 1992/07/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Bio-Cybernetics
neural network,  neural controller,  random search,  learning control,  

Full Text: PDF(465.7KB)>>
Buy this Article

A learning algorithm for neural controllers based on random search is proposed. The method presents an attractive feature in comparison with the learning of neural controllers using the standard backpropagation method. Namely, in this approach the identification of the unknown plant becomes unnecessary because the parameters of the controller are determined by a trial and error process. This is a favorable feature particularly in cases in which the characteristics of the system are complicated and consequently the identification is difficult or impossible to perform at all. As application examples, the learning control of the pendulum system and the maze problem are shown.