Presentation 2007-01-17
A Simple Construction Method for the States of Chaos Control Using Reinforcement Learning
Norihisa SATO, Masaharu ADACHI, Makoto KOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) A method for control of chaos with reinforcement learning is proposed by Gadaleta et al.. The method can contorl a chaotic behavior to a fixed point or a periodic solution even if one does not knwow the position of the target point(s). However, the reinfocement learning is a trial and error process, therefore we often fail to control. The success rate of control is depend on the states of the reinfocement learning. Then, we propose a simple construction method for the states of chaos control using reinforcement learning. The method requires less computational costs for preparation of the states than the conventional method.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) control of chaos / reinforcement learning
Paper # NLP2006-124
Date of Issue

Conference Information
Committee NLP
Conference Date 2007/1/10(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) A Simple Construction Method for the States of Chaos Control Using Reinforcement Learning
Sub Title (in English)
Keyword(1) control of chaos
Keyword(2) reinforcement learning
1st Author's Name Norihisa SATO
1st Author's Affiliation Graduate School of Advanced Science and Technology, Tokyo Denki University()
2nd Author's Name Masaharu ADACHI
2nd Author's Affiliation Graduate School of Advanced Science and Technology, Tokyo Denki University
3rd Author's Name Makoto KOTANI
3rd Author's Affiliation Graduate School of Advanced Science and Technology, Tokyo Denki University
Date 2007-01-17
Paper # NLP2006-124
Volume (vol) vol.106
Number (no) 451
Page pp.pp.-
#Pages 6
Date of Issue