Fast seed-learning algorithms for games

Jialin LIU*, Olivier TEYTAUD, Tristan CAZENAVE

*Corresponding author for this work

Research output: Book Chapters | Papers in Conference ProceedingsConference paper (refereed)Referred Conference Paperpeer-review

6 Citations (Scopus)

Abstract

Recently, a methodology has been proposed for boosting the computational intelligence of randomized game-playing programs. We propose faster variants of these algorithms, namely rectangular algorithms (fully parallel) and bandit algorithms (faster in a sequential setup). We check the performance on several board games and card games. In addition, in the case of Go, we check the methodology when the opponent is completely distinct to the one used in the training.

Original languageEnglish
Title of host publicationComputers and Games : 9th International Conference, CG 2016, Revised Selected Papers
EditorsAske PLAAT, Walter KOSTERS, Jaap VAN DEN HERIK
PublisherSpringer-Verlag Italia Srl
Pages58-70
Number of pages13
ISBN (Print)9783319509341
DOIs
Publication statusPublished - 2016
Externally publishedYes
Event9th International Conference on Computer and Games, CG 2016 - Leiden, Netherlands
Duration: 29 Jun 20161 Jul 2016

Publication series

NameLecture Notes in Computer Science
PublisherSpringer
Volume10068
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349
NameTheoretical Computer Science and General Issues
PublisherSpringer
ISSN (Print)2512-2010
ISSN (Electronic)2512-2029

Conference

Conference9th International Conference on Computer and Games, CG 2016
Country/TerritoryNetherlands
CityLeiden
Period29/06/161/07/16

Bibliographical note

Publisher Copyright:
© Springer International Publishing AG 2016.

Fingerprint

Dive into the research topics of 'Fast seed-learning algorithms for games'. Together they form a unique fingerprint.

Cite this