Show simple item record

dc.contributor.authorJouandeau, Nicolas
dc.contributor.authorCazenave, Tristan
dc.date.accessioned2020-06-25T11:46:51Z
dc.date.available2020-06-25T11:46:51Z
dc.date.issued2014
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/20899
dc.language.isoenen
dc.subjectPerfect Informationen
dc.subjectStochastic Gameen
dc.subjectMain Loopen
dc.subjectClassical Moveen
dc.subjectSelect Functionen
dc.subject.ddc006.3en
dc.titleMonte-Carlo Tree Reductions for Stochastic Gamesen
dc.typeCommunication / Conférence
dc.description.abstractenMonte-Carlo Tree Search (MCTS) is a powerful paradigm for perfect information games. When considering stochastic games, the tree model that represents the game has to take chance and a huge branching factor into account. As effectiveness of MCTS may decrease in such a setting, tree reductions may be useful. Chance-nodes are a way to deal with random events. Move-groups are another way to deal efficiently with a large branching factor by regrouping nodes. Group-nodes are regrouping only reveal moves and enable a choice between reveal moves and classical moves. We present various policies to use such reductions for the stochastic game Chinese Dark Chess. Move-groups, chance-nodes and group-nodes are compared.en
dc.identifier.citationpages228-238en
dc.relation.ispartoftitleTechnologies and Applications of Artificial Intelligenceen
dc.relation.ispartofeditorCheng, Shin-Ming
dc.relation.ispartofeditorDay, Min-Yuh
dc.relation.ispartofpublnameSpringeren
dc.relation.ispartofpages396en
dc.relation.ispartofurl10.1007/978-3-319-13987-6en
dc.identifier.urlsitehttps://hal.archives-ouvertes.fr/hal-02317159en
dc.subject.ddclabelIntelligence artificielleen
dc.relation.ispartofisbn978-3-319-13986-9en
dc.relation.conftitle19th International Conference, TAAI 2014en
dc.relation.confdate2014-11
dc.relation.confcityTaipeien
dc.relation.confcountry"Taiwanen
dc.relation.forthcomingnonen
dc.identifier.doi10.1007/978-3-319-13987-6_22en
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewednonen
dc.relation.Isversionofjnlpeerreviewednonen
dc.date.updated2020-06-25T11:38:04Z
hal.person.labIds
hal.person.labIds989


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record