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, RichardORCID iD for 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
Keyword(s) multiobjective reinforcement learning
ϵ-greedy exploration
optimistic initialisation
science & 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

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 15 times in TR Web of Science
Scopus Citation Count Cited 19 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 310 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