Fuzzy Q-Learning with the Modified ART Neural Network

Authors:
Hirokae Oeda;Noaki Hanada;Hideake Kimoto;Takeshi Naraki;Kenichi Takahashi;Tetsuhiro Miyahara
Affiliations:
Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan;Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan;Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan;Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan;Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan;Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan
Venue:
IAT '05 Proceedings of the IEEE/WIC/ACM International Conference on Intelligent Agent Technology
Year:
2005

Citing 0
Cited 4

A Comparative Study of Parallel Reinforcement Learning Methods with a PC Cluster System

IAT '06 Proceedings of the IEEE/WIC/ACM international conference on Intelligent Agent Technology
State Space Segmentation for Acquisition of Agent Behavior

IAT '06 Proceedings of the IEEE/WIC/ACM international conference on Intelligent Agent Technology
Direct code access in self-organizing neural networks for reinforcement learning

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Continuous state/action reinforcement learning: A growing self-organizing map approach

Neurocomputing

Quantified Score

Hi-index	0.02

Visualization

Abstract

We present a methiod to acquire rules for agent behavior, where continues numeric percepts are classified into categories by fuzzy ART and fuzzy Q-Learning is employed to acquire rules. To make fuzzy such that it slects some categories for a percept vector and returns them with their fitness values. For efficient learning, we also present method that integrates two ctaegories into one, where we define the similarity for any category pair and it is utilized for integration.Moreover, a vigilance parameter is defined for all categories. The methods and some experiments have been done.