Presentation 2002/6/18
The Influence of The Number of Prototypes and Perturbations in Controlling Chaos with Reinforcement Learning
Norihisa SATO, Masaharu ADACHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this article, modifications of a. method for controlling chaos with reinforcement learning proposed by Gadaleta et al. are proposed in order to overcome difficulties of the original control method for high periodic orbits or coupled chaotic systems. We considered reducing the number of prototypes for the reinforcement learning and numbers of perturbations and the period for the application of them. It is found that the modified control can stabilize the higher periodic orbit in a chaotic neural network with two neurons. The results suggest that the modified control method might be useful for high dimensional systems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) control of chaos / reinforcement lerning / chaotic neural networks
Paper # NLP2002-23
Date of Issue

Conference Information
Committee NLP
Conference Date 2002/6/18(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) The Influence of The Number of Prototypes and Perturbations in Controlling Chaos with Reinforcement Learning
Sub Title (in English)
Keyword(1) control of chaos
Keyword(2) reinforcement lerning
Keyword(3) chaotic neural networks
1st Author's Name Norihisa SATO
1st Author's Affiliation Department of Electronic Engineering,Tokyo Denki University()
2nd Author's Name Masaharu ADACHI
2nd Author's Affiliation Department of Electronic Engineering,Tokyo Denki University
Date 2002/6/18
Paper # NLP2002-23
Volume (vol) vol.102
Number (no) 142
Page pp.pp.-
#Pages 4
Date of Issue