Show simple item record

dc.contributor.authorCazenave, Tristan
dc.date.accessioned2019-04-12T14:46:53Z
dc.date.available2019-04-12T14:46:53Z
dc.date.issued2017
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/18645
dc.descriptionLNCS n°10664en
dc.language.isoenen
dc.subjectdistributed computingen
dc.subjectcombinatorial gameen
dc.subjectGo gameen
dc.subject.ddc006.3en
dc.titleImproved Policy Networks for Computer Goen
dc.typeCommunication / Conférence
dc.description.abstractenGolois uses residual policy networks to play Go. Two improvements to these residual policy networks are proposed and tested. The first one is to use three output planes. The second one is to add Spatial Batch Normalization.en
dc.identifier.citationpages90-100en
dc.relation.ispartoftitleAdvances in Computer Games, 15th International Conferences, ACG 2017, Revised Selected Papersen
dc.relation.ispartofeditorWinands, Mark H.M.
dc.relation.ispartofeditorvan den Herik, H. Jaap
dc.relation.ispartofeditorKosters, Walter A.
dc.relation.ispartofpublnameSpringeren
dc.relation.ispartofpublcityBerlin Heidelbergen
dc.relation.ispartofdate2017
dc.relation.ispartofpages235en
dc.relation.ispartofurl10.1007/978-3-319-71649-7en
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-3-319-71648-0en
dc.relation.conftitle15th International Conferences (ACG 2017)en
dc.relation.confdate2017-07
dc.relation.confcityLeidenen
dc.relation.confcountryNetherlandsen
dc.relation.forthcomingnonen
dc.identifier.doi10.1007/978-3-319-71649-7_8en
dc.description.ssrncandidatenonen
dc.description.halcandidateouien
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2019-03-27T15:05:33Z
hal.person.labIds989
hal.identifierhal-02098463*


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record