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

Auckland, New Zealand December 13-December 15

DOI Bookmark:

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

Sixth International Conference on Hyb ...

	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 Hiroyuki Fujii Articles by Kazuyuki Ito Articles by Akio Gofuku

	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

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.