Show simple item record

dc.contributor.authorMannor, Shie
dc.contributor.authorTsitsiklis, John N.
dc.date.accessioned2013-07-01T20:24:53Z
dc.date.available2013-07-01T20:24:53Z
dc.date.issued2011-06
dc.identifier.isbn9781450306195
dc.identifier.isbn1450306195
dc.identifier.urihttp://hdl.handle.net/1721.1/79401
dc.description.abstractWe consider finite horizon Markov decision processes under performance measures that involve both the mean and the variance of the cumulative reward. We show that either randomized or history-based policies can improve performance. We prove that the complexity of computing a policy that maximizes the mean reward under a variance constraint is NP-hard for some cases, and strongly NP-hard for others. We finally offer pseudo-polynomial exact and approximation algorithms.en_US
dc.description.sponsorshipNational Science Foundation (U.S.) (grant CMMI-0856063)en_US
dc.description.sponsorshipIsrael Science Foundation (contract 890015)en_US
dc.description.sponsorshipTechnion, Israel Institute of Technology (Horeb Fellowship)en_US
dc.language.isoen_US
dc.publisherInternational Machine Learning Societyen_US
dc.relation.isversionofhttp://www.icml-2011.org/papers.phpen_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike 3.0en_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/en_US
dc.sourceTsitsiklis via Amy Stouten_US
dc.titleMean-Variance Optimization in Markov Decision Processesen_US
dc.typeArticleen_US
dc.identifier.citationMannor, Shie and John Tsitsiklis. "Mean-Variance Optimization in Markov Decision Processes ." in Twenty-Eighth International Conference on Machine Learning, ICML 2011, Jun. 28-Jul.2, Bellevue, Washington. 2011.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Department of Electrical Engineering and Computer Scienceen_US
dc.contributor.mitauthorTsitsiklis, John N.en_US
dc.relation.journalProceedings of the Twenty-Eighth International Conference on Machine Learning, ICML 2011en_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/ConferencePaperen_US
eprint.statushttp://purl.org/eprint/status/NonPeerRevieweden_US
dspace.orderedauthorsMannor, Shie; Tsitsiklis, Johnen_US
dc.identifier.orcidhttps://orcid.org/0000-0003-2658-8239
mit.licenseOPEN_ACCESS_POLICYen_US
mit.metadata.statusComplete


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record