Clinical data based optimal STI strategies for HIV: a reinforcement learning approach

Reference : Clinical data based optimal STI strategies for HIV: a reinforcement learning approach


	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Life sciences : Multidisciplinary, general & others Engineering, computing & technology : Multidisciplinary, general & others
	To cite this reference:	http://hdl.handle.net/10993/20439

Title :	Clinical data based optimal STI strategies for HIV: a reinforcement learning approach
Language :	English
Author, co-author :	Ernst, D. []
	Stan, G.B. []
	Goncalves, Jorge [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
	Wehenkel, L. []
Publication date :	2006
Main document title :	Proceedings of the IEEE Conference on Decision and Control
Publisher :	IEEE
Pages :	667 - 672
Peer reviewed :	Yes
ISBN :	1424401712
Event name :	45th IEEE Conference on Decision and Control
Event date :	13-15 December 2006
Event place (city) :	San Diego
Event country :	USA
Abstract :	[en] This paper addresses the problem of computing optimal structured treatment interruption strategies for HIV infected patients. We show that reinforcement learning may be useful to extract such strategies directly from clinical data, without the need of an accurate mathematical model of HIV infection dynamics. To support our claims, we report simulation results obtained by running a recently proposed batch-mode reinforcement learning algorithm, known as fitted Q iteration, on numerically generated data.
Permalink :	http://hdl.handle.net/10993/20439
DOI :	10.1109/CDC.2006.377527

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Limited access	Clinical data based optimal STI strategies for HIV.pdf		Publisher postprint	141.36 kB	Request a copy

All documents in ORBi^lu are protected by a user license.