Evolving Policies for Multi-Reward Partially Observable Markov Decision Processes (MR-POMDPs)

File Description SizeFormat 
gecco.pdfAccepted version782.13 kBUnknownView/Open
Title: Evolving Policies for Multi-Reward Partially Observable Markov Decision Processes (MR-POMDPs)
Authors: Soh, H
Demiris, Y
Item Type: Conference Paper
Editors: Krasnogor, N
Issue Date: 16-Jul-2011
URI: http://hdl.handle.net/10044/1/20001
DOI: http://dx.doi.org/10.1145/2001576.2001674
Publisher: ASSOC COMPUTING MACHINERY
Start Page: 713
End Page: 720
Journal / Book Title: GECCO-2011: PROCEEDINGS OF THE 13TH ANNUAL GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE
Copyright Statement: © 2011 ACM. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in PROCEEDINGS OF THE GECCO, (2011) http://doi.acm.org/10.1145/10.1145/2001576.2001674
Conference Name: 13th Annual Genetic and Evolutionary Computation Conference (GECCO)
Publication Status: Published
Start Date: 2011-07-12
Finish Date: 2011-07-16
Conference Place: Dublin, IRELAND
Appears in Collections:Electrical and Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons