Show simple item record

Strong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processes

hal.structure.identifierCentre d'économie de la Sorbonne [CES]
dc.contributor.authorVenel, Xavier
HAL ID: 8219
ORCID: 0000-0003-1150-9139
hal.structure.identifierCEntre de REcherches en MAthématiques de la DEcision [CEREMADE]
dc.contributor.authorZiliotto, Bruno
dc.date.accessioned2019-11-08T10:44:08Z
dc.date.available2019-11-08T10:44:08Z
dc.date.issued2016
dc.identifier.issn0363-0129
dc.identifier.urihttps://basepub.dauphine.fr/handle/123456789/20210
dc.language.isoenen
dc.subjectdynamic programmingen
dc.subjectMarkov decision processesen
dc.subjectpartial observationen
dc.subjectuniform valueen
dc.subjectlong-run average payoffen
dc.subject.ddc515en
dc.titleStrong Uniform Value in Gambling Houses and Partially Observable Markov Decision Processesen
dc.typeArticle accepté pour publication ou publié
dc.description.abstractenIn several standard models of dynamic programming (gambling houses, MDPs, POMDPs), we prove the existence of a robust notion of value for the infinitely repeated problem, namely the strong uniform value. This solves two open problems. First, this shows that for any > 0, the decision-maker has a pure strategy σ which is-optimal in any n-stage problem, provided that n is big enough (this result was only known for behavior strategies, that is, strategies which use randomization). Second, for any > 0, the decision-maker can guarantee the limit of the n-stage value minus in the infinite problem where the payoff is the expectation of the inferior limit of the time average payoff.en
dc.relation.isversionofjnlnameSIAM Journal on Control and Optimization
dc.relation.isversionofjnlvol54en
dc.relation.isversionofjnlissue4en
dc.relation.isversionofjnldate2016-08
dc.relation.isversionofjnlpages1983-2008en
dc.relation.isversionofdoi10.1137/15M1043340en
dc.relation.isversionofjnlpublisherSIAM - Society for Industrial and Applied Mathematicsen
dc.subject.ddclabelAnalyseen
dc.relation.forthcomingnonen
dc.relation.forthcomingprintnonen
dc.description.ssrncandidatenonen
dc.description.halcandidatenonen
dc.description.readershiprechercheen
dc.description.audienceInternationalen
dc.relation.Isversionofjnlpeerreviewedouien
dc.relation.Isversionofjnlpeerreviewedouien
dc.date.updated2019-11-08T10:40:33Z
hal.author.functionaut
hal.author.functionaut


Files in this item

Thumbnail
Name:
Revision_venel_ziliotto5.pdf
Size:
423.0Kb
Format:
PDF
View/Open

This item appears in the following Collection(s)

Show simple item record