Show simple item record

hal.structure.identifierLaboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
dc.contributor.authorCazenave, Tristan
HAL ID: 743184
dc.date.accessioned2017-01-16T13:56:57Z
dc.date.available2017-01-16T13:56:57Z
dc.date.issued2015
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/16166
dc.language.isoenen
dc.subjectMonte Carlo Tree Searchen
dc.subject.ddc006en
dc.titleGeneralized Rapid Action Value Estimationen
dc.typeCommunication / Conférence
dc.description.abstractenMonte Carlo Tree Search (MCTS) is the state of the art algorithm for many games including the game of Go and General Game Playing (GGP). The standard algorithm for MCTS is Upper Confidence bounds applied to Trees (UCT). For games such as Go a big improvement over UCT is the Rapid Action Value Estimation (RAVE) heuristic. We propose to generalize the RAVE heuristic so as to have more accurate estimates near the leaves. We test the resulting algorithm named GRAVE for Atarigo, Knighthrough, Domineering and Go.en
dc.identifier.citationpages754-760en
dc.relation.ispartoftitleIJCAI'15 Proceedings of the 24th International Conference on Artificial Intelligenceen
dc.relation.ispartofeditorYang, Qiang
dc.relation.ispartofeditorWooldridge, Michael
dc.relation.ispartofpublnameAAAI Pressen
dc.relation.ispartofpublcityPalo Alto (USA)en
dc.relation.ispartofdate2015-07
dc.relation.ispartofpages1199en
dc.subject.ddclabelMéthodes informatiques spécialesen
dc.relation.ispartofisbn978-1-57735-738-4en
dc.relation.conftitle24th International Conference on Artificial Intelligenceen
dc.relation.confdate2015-07
dc.relation.confcityBuenos Airesen
dc.relation.confcountryArgentinaen
dc.relation.forthcomingnonen
dc.description.ssrncandidatenonen
dc.description.halcandidateouien
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2017-01-16T11:49:52Z
hal.identifierhal-01436522*
hal.version1*
hal.update.actionupdateFiles*
hal.author.functionaut


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record