Softmax exploration strategies for multiobjective reinforcement learning

Vamplew, Peter, Dazeley, Richard and Foale, Cameron 2017, Softmax exploration strategies for multiobjective reinforcement learning, Neurocomputing, vol. 263, pp. 74-86, doi: 10.1016/j.neucom.2016.09.141.

Attached Files
Name Description MIMEType Size Downloads

Title Softmax exploration strategies for multiobjective reinforcement learning
Author(s) Vamplew, Peter
Dazeley, Richard
Foale, Cameron
Journal name Neurocomputing
Volume number 263
Start page 74
End page 86
Total pages 13
Publisher Elsevier
Place of publication Amsterdam, The Netherlands
Publication date 2017-11-08
ISSN 0925-2312
1872-8286
Keyword(s) multiobjective reinforcement learning
exploration
ϵ-greedy exploration
optimistic initialisation
softmax
science & technology
technology
computer science, artificial intelligence
computer science
epsilon-greedy exploration
Language eng
DOI 10.1016/j.neucom.2016.09.141
Field of Research 08 Information And Computing Sciences
09 Engineering
17 Psychology And Cognitive Sciences
HERDC Research category C1.1 Refereed article in a scholarly journal
ERA Research output type C Journal article
Copyright notice ©2017, Elsevier B.V.
Persistent URL http://hdl.handle.net/10536/DRO/DU:30109283

Document type: Journal Article
Collection: School of Information Technology
Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 4 Abstract Views, 4 File Downloads  -  Detailed Statistics
Created: Tue, 26 Jun 2018, 09:05:02 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.