An improved approach to reinforcement learning in computer go

Dann, M, Zambetta, F and Thangarajah, J 2015, 'An improved approach to reinforcement learning in computer go', in Proceedings of the Computational Intelligence and Games (IEEE CIG 2015), Tainan, Taiwan, 31 August - 2 September 2015, pp. 169-176.


Document type: Conference Paper
Collection: Conference Papers

Attached Files
Name Description MIMEType Size
n2006056655.pdf Accepted Manuscript application/pdf 413.56KB
Title An improved approach to reinforcement learning in computer go
Author(s) Dann, M
Zambetta, F
Thangarajah, J
Year 2015
Conference name IEEE CIG 2015
Conference location Tainan, Taiwan
Conference dates 31 August - 2 September 2015
Proceedings title Proceedings of the Computational Intelligence and Games (IEEE CIG 2015)
Publisher IEEE
Place of publication United States
Start page 169
End page 176
Total pages 8
Abstract Monte-Carlo Tree Search (MCTS) has revolutionized, Computer Go, with programs based on the algorithm, achieving a level of play that previously seemed decades away., However, since the technique involves constructing a search tree, its performance te
Subjects Adaptive Agents and Intelligent Robotics
Neural, Evolutionary and Fuzzy Computation
DOI - identifier 10.1109/CIG.2015.7317910
Copyright notice © 2015 IEEE
ISBN 9781479986217
Additional Notes “©2015 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Versions
Version Filter Type
Altmetric details:
Access Statistics: 59 Abstract Views, 39 File Downloads  -  Detailed Statistics
Created: Thu, 10 Dec 2015, 08:07:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us