Emergence of Information Processor Using Real World--Real-Time Learning of Pursuit Problem

	This Article
	Subscribers, please Login Purchase article: $19 PDF RSS feed
	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 Hiroyuki Fujii Articles by Kazuyuki Ito Articles by Akio Gofuku

Sixth International Conference on Hybrid Intelligent Systems (HIS'06)

Auckland, New Zealand

December 13-December 15

ISBN: 0-7695-2662-4

	ASCII Text	x
	Hiroyuki Fujii, Kazuyuki Ito, Akio Gofuku, "Emergence of Information Processor Using Real World--Real-Time Learning of Pursuit Problem," Hybrid Intelligent Systems, International Conference on, pp. 7, Sixth International Conference on Hybrid Intelligent Systems (HIS'06), 2006.

	BibTex	x
	@article{ 10.1109/HIS.2006.23, author = {Hiroyuki Fujii and Kazuyuki Ito and Akio Gofuku}, title = {Emergence of Information Processor Using Real World--Real-Time Learning of Pursuit Problem}, journal ={Hybrid Intelligent Systems, International Conference on}, volume = {0}, year = {2006}, isbn = {0-7695-2662-4}, pages = {7}, doi = {http://doi.ieeecomputersociety.org/10.1109/HIS.2006.23}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Hybrid Intelligent Systems, International Conference on TI - Emergence of Information Processor Using Real World--Real-Time Learning of Pursuit Problem SN - 0-7695-2662-4 SP EP A1 - Hiroyuki Fujii, A1 - Kazuyuki Ito, A1 - Akio Gofuku, PY - 2006 KW - null VL - 0 JA - Hybrid Intelligent Systems, International Conference on ER -

Hiroyuki Fujii, Okayama University, Japan

Kazuyuki Ito, Hosei University, Japan

Akio Gofuku, Okayama University, Japan

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/HIS.2006.23

Real-time reinforcement learning is difficult because number of trials is too much to complete learning within limited time.

To solve the problem, we consider reduction of action-state space by information processor using real world without prior knowledge. We obtain the information processor in evolution by setting the fitness as ease of learning. As a typical example, we address pursuit problem in which dynamics is regarded. As a result, the processor has been obtained in evolution and agent has learned in real-time.

Citation:

Hiroyuki Fujii, Kazuyuki Ito, Akio Gofuku, "Emergence of Information Processor Using Real World--Real-Time Learning of Pursuit Problem," his, pp.7, Sixth International Conference on Hybrid Intelligent Systems (HIS'06), 2006

Peer Review Notice | Give Us Feedback

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