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

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers 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 Masayuki Kushida Articles by Kenichi Takahashi Articles by Hiroaki Ueda Articles by Tetsuhiro Miyahara

2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'06)

Hong Kong, China

December 18-December 22

ISBN: 0-7695-2748-5

	ASCII Text	x
	Masayuki Kushida, Kenichi Takahashi, Hiroaki Ueda, Tetsuhiro Miyahara, "A Comparative Study of Parallel Reinforcement Learning Methods with a PC Cluster System," Intelligent Agent Technology, IEEE / WIC / ACM International Conference on, pp. 416-419, 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'06), 2006.

	BibTex	x
	@article{ 10.1109/IAT.2006.3, author = {Masayuki Kushida and Kenichi Takahashi and Hiroaki Ueda and Tetsuhiro Miyahara}, title = {A Comparative Study of Parallel Reinforcement Learning Methods with a PC Cluster System}, journal ={Intelligent Agent Technology, IEEE / WIC / ACM International Conference on}, volume = {0}, year = {2006}, isbn = {0-7695-2748-5}, pages = {416-419}, doi = {http://doi.ieeecomputersociety.org/10.1109/IAT.2006.3}, 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 - A Comparative Study of Parallel Reinforcement Learning Methods with a PC Cluster System SN - 0-7695-2748-5 SP416 EP419 A1 - Masayuki Kushida, A1 - Kenichi Takahashi, A1 - Hiroaki Ueda, A1 - Tetsuhiro Miyahara, PY - 2006 KW - null VL - 0 JA - Intelligent Agent Technology, IEEE / WIC / ACM International Conference on ER -

Masayuki Kushida, Hiroshima City University, Japan

Kenichi Takahashi, Hiroshima City University, Japan

Hiroaki Ueda, Hiroshima City University, Japan

Tetsuhiro Miyahara, Hiroshima City University, Japan

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IAT.2006.3

This paper presents a comparative study of three parallel implementation models for reinforcement learning. Two of them utilize Q-learning, and the other one utilizes fuzzy Q-learning for agent learning. In order to evaluate performance and validity of the three method, a PC(personal computer) cluster system consisting of 16 PCs connected via Gigabit ethernet has been built. For communications to deliver data among PCs, MPI (Message Passing Interface) is employed. Experimental results are compared with one another to show the performance and characteristics of the three methods.

Citation:

Masayuki Kushida, Kenichi Takahashi, Hiroaki Ueda, Tetsuhiro Miyahara, "A Comparative Study of Parallel Reinforcement Learning Methods with a PC Cluster System," iat, pp.416-419, 2006 IEEE/WIC/ACM International Conference on Intelligent Agent Technology (IAT'06), 2006

Peer Review Notice | Give Us Feedback

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