Show simple item record

dc.contributor.authorCazenave, Tristan
dc.date.accessioned2017-01-16T11:02:59Z
dc.date.available2017-01-16T11:02:59Z
dc.date.issued2015
dc.identifier.issn1943-068X
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/16164
dc.language.isoenen
dc.subjectUCTen
dc.subjectMonte Carlo Tree Searchen
dc.subjectSequential Halvingen
dc.subjectNogoen
dc.subjectSequential halving applied to trees (SHOT)en
dc.subject.ddc006.3en
dc.titleSequential Halving Applied to Treesen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenMonte Carlo tree search (MCTS) is state of the art for multiple games and problems. The base algorithm currently used for MCTS is UCT. We propose an alternative MCTS algorithm: sequential halving applied to Trees (SHOT). It has multiple advantages over UCT: it spends less time in the tree, it uses less memory, it is parameter free, at equal time settings it beats UCT for a complex combinatorial game and it can be efficiently parallelized.en
dc.relation.isversionofjnlnameIEEE Transactions on Computational Intelligence and AI in Games
dc.relation.isversionofjnlvol7en
dc.relation.isversionofjnlissue1en
dc.relation.isversionofjnldate2015-03
dc.relation.isversionofjnlpages102-105en
dc.relation.isversionofdoi10.1109/TCIAIG.2014.2317737en
dc.relation.isversionofjnlpublisherIEEEen
dc.subject.ddclabelIntelligence artificielleen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenonen
dc.description.halcandidateouien
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewedouien
dc.relation.Isversionofjnlpeerreviewedouien
dc.date.updated2017-01-16T10:55:04Z
hal.person.labIds989
hal.identifierhal-01436255*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record