Fuzzy Q-Learning with the Modified ART Neural Network

Compi?gne University of Technology, France September 19-September 22

DOI Bookmark:

http://doi.ieeecomputersociety.org/10.1109/IAT.2005.78

2005 IEEE/WIC/ACM International Confe ...

	This Article
	PURCHASE ARTICLE: $19 PDF HTML IEEE Xplore Subscribers
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan/Endnote
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Hirokae Oeda Articles by Noaki Hanada Articles by Hideake Kimoto Articles by Takeshi Naraki Articles by Kenichi Takahashi Articles by Tetsuhiro Miyahara

	ASCII Text	x
	Hirokae Oeda, Noaki Hanada, Hideake Kimoto, Takeshi Naraki, Kenichi Takahashi, Tetsuhiro Miyahara, "Fuzzy Q-Learning with the Modified ART Neural Network," Intelligent Agent Technology, IEEE / WIC / ACM International Conference on, pp. 308-305, 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'05), 2005.

	BibTex	x
	@article{ 10.1109/IAT.2005.78, author = {Hirokae Oeda and Noaki Hanada and Hideake Kimoto and Takeshi Naraki and Kenichi Takahashi and Tetsuhiro Miyahara}, title = {Fuzzy Q-Learning with the Modified ART Neural Network}, journal ={Intelligent Agent Technology, IEEE / WIC / ACM International Conference on}, volume = {0}, year = {2005}, isbn = {0-7695-2416-8}, pages = {308-305}, doi = {http://doi.ieeecomputersociety.org/10.1109/IAT.2005.78}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Intelligent Agent Technology, IEEE / WIC / ACM International Conference on TI - Fuzzy Q-Learning with the Modified ART Neural Network SN - 0-7695-2416-8 SP308 EP305 A1 - Hirokae Oeda, A1 - Noaki Hanada, A1 - Hideake Kimoto, A1 - Takeshi Naraki, A1 - Kenichi Takahashi, A1 - Tetsuhiro Miyahara, PY - 2005 KW - null VL - 0 JA - Intelligent Agent Technology, IEEE / WIC / ACM International Conference on ER -

Hirokae Oeda, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

Noaki Hanada, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

Hideake Kimoto, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

Takeshi Naraki, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

Kenichi Takahashi, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

Tetsuhiro Miyahara, Department of Intelligent Systems, Hiroshima City University, Hiroshima, Japan

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.

Citation:

Hirokae Oeda, Noaki Hanada, Hideake Kimoto, Takeshi Naraki, Kenichi Takahashi, Tetsuhiro Miyahara, "Fuzzy Q-Learning with the Modified ART Neural Network," iat, pp.308-305, 2005 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'05), 2005

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.