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.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Victor WILLIAMS, Kiyotoshi MATSUOKA, "Learning of Neural Controllers by Random Search Technique" in IEICE TRANSACTIONS on Information,
vol. E75-D, no. 4, pp. 595-601, July 1992, doi: .
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/e75-d_4_595/_p
Copy
@ARTICLE{e75-d_4_595,
author={Victor WILLIAMS, Kiyotoshi MATSUOKA, },
journal={IEICE TRANSACTIONS on Information},
title={Learning of Neural Controllers by Random Search Technique},
year={1992},
volume={E75-D},
number={4},
pages={595-601},
abstract={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.},
keywords={},
doi={},
ISSN={},
month={July},}
Copy
TY - JOUR
TI - Learning of Neural Controllers by Random Search Technique
T2 - IEICE TRANSACTIONS on Information
SP - 595
EP - 601
AU - Victor WILLIAMS
AU - Kiyotoshi MATSUOKA
PY - 1992
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E75-D
IS - 4
JA - IEICE TRANSACTIONS on Information
Y1 - July 1992
AB - 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.
ER -