Presentation 2004/3/12
A State-Space Construction for Reinforcement Learning Using Fuzzy-ART Neural Network
Takeshi KAMIO, Satomi SOGA, Kunihiko MITSUBORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) If the continuous perceptual inputs are given to the agent in the reinforcement learning, they have to be classified into appropriate states. The state-space construction is very important because it affects the achievement of the task. Recently, several researchers have reported that the adaptive resonance theory (ART) neural network can be used to construct the state-space adaptively. However, most of them have simply used the ART network as the classifier for the perceptual inputs. In this report, we propose a new state-space construction method by Fuzzy-ART network, which is synthesized according to the results of the reinforcement learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Reinforcement Learning / State-Space / Adaptive Resonance Theory / Fuzzy-ART
Paper # NC2003-201
Date of Issue

Conference Information
Committee NC
Conference Date 2004/3/12(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A State-Space Construction for Reinforcement Learning Using Fuzzy-ART Neural Network
Sub Title (in English)
Keyword(1) Reinforcement Learning
Keyword(2) State-Space
Keyword(3) Adaptive Resonance Theory
Keyword(4) Fuzzy-ART
1st Author's Name Takeshi KAMIO
1st Author's Affiliation Hiroshima City University()
2nd Author's Name Satomi SOGA
2nd Author's Affiliation Hiroshima City University
3rd Author's Name Kunihiko MITSUBORI
3rd Author's Affiliation Japan Coast Guard Academy
Date 2004/3/12
Paper # NC2003-201
Volume (vol) vol.103
Number (no) 734
Page pp.pp.-
#Pages 6
Date of Issue