Presentation 2005-01-24
A Detection Method of Environmental Changes for Reinforcement Learning
Tetsuya TAKAHASHI, Masaharu ADACHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Reinforcement learning is a kind of learning systems which can deal with an unknown environment. In the reinforcement learning, an agent learns the optimal actions by applying a trial-and-error to an environment. Therefore. it is known that it can apply also to a dynamic environment. It is already reported that the method of adjusting specific parameters in the reinforcement learning is effective, when an agent learns a dynamic environment. The method for adjusting the parameters is known as meta-learning in the reinforcement learning. In this article, we propose a novel method for detecting environmental changes in the reinforcement learning. The proposed method utilizes recurrence plots of a state transition of an agent, and quantify changes of the recurrence plot by a texture analysis. It is shown that the proposed method is effective to detect environmental changes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) reinforcement learning / environmental changes / recurrence plots
Paper # NLP2004-95
Date of Issue

Conference Information
Committee NLP
Conference Date 2005/1/17(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 Detection Method of Environmental Changes for Reinforcement Learning
Sub Title (in English)
Keyword(1) reinforcement learning
Keyword(2) environmental changes
Keyword(3) recurrence plots
1st Author's Name Tetsuya TAKAHASHI
1st Author's Affiliation Department of Electronic Engineering, Graduate School of Engineering, Tokyo Denki University /()
2nd Author's Name Masaharu ADACHI
2nd Author's Affiliation
Date 2005-01-24
Paper # NLP2004-95
Volume (vol) vol.104
Number (no) 583
Page pp.pp.-
#Pages 6
Date of Issue