Performance Evaluation of TD-Learning Methods for Bandwidth Provisioning

	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 M. Jahanshahi Articles by M. R. Meybodi

7th IEEE International Conference on Computer and Information Technology (CIT 2007)

Aizu-Wakamatsu City, Fukushima, Japan

October 16-October 19

ISBN: 0-7695-2983-6

	ASCII Text	x
	M. Jahanshahi, M. R. Meybodi, "Performance Evaluation of TD-Learning Methods for Bandwidth Provisioning," Computer and Information Technology, International Conference on, pp. 171-176, 7th IEEE International Conference on Computer and Information Technology (CIT 2007), 2007.

	BibTex	x
	@article{ 10.1109/CIT.2007.131, author = {M. Jahanshahi and M. R. Meybodi}, title = {Performance Evaluation of TD-Learning Methods for Bandwidth Provisioning}, journal ={Computer and Information Technology, International Conference on}, volume = {0}, year = {2007}, isbn = {0-7695-2983-6}, pages = {171-176}, doi = {http://doi.ieeecomputersociety.org/10.1109/CIT.2007.131}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Computer and Information Technology, International Conference on TI - Performance Evaluation of TD-Learning Methods for Bandwidth Provisioning SN - 0-7695-2983-6 SP171 EP176 A1 - M. Jahanshahi, A1 - M. R. Meybodi, PY - 2007 VL - 0 JA - Computer and Information Technology, International Conference on ER -

M. Jahanshahi, Islamic Azad University - Central Tehran Branch

M. R. Meybodi, Amirkabir University of Technology

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CIT.2007.131

Q-learning and SARSA are two methods of TD- learning. Researchers interested in this field proposed the Eligibility concept in order to speed up Q-learning and SARSA. They proved their claim by running the algorithms in a static environment. Authors of this paper have used Q-learning, SARSA and also their eligibility versions for bandwidth provisioning in DiffServ networks that is an absolutely dynamic environment. Performance of these methods in this absolutely dynamic environment is evaluated. Keyword - Queuing delay guarantee, Bandwidth provisioning, DiffServ architecture, TD-learning

Citation:

M. Jahanshahi, M. R. Meybodi, "Performance Evaluation of TD-Learning Methods for Bandwidth Provisioning," cit, pp.171-176, 7th IEEE International Conference on Computer and Information Technology (CIT 2007), 2007

Peer Review Notice | Give Us Feedback

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