Show simple item record

dc.contributor.authorDesai, Vijay V.
dc.contributor.authorFarias, Vivek F.
dc.contributor.authorMoallemi, Ciamac C.
dc.date.accessioned2012-11-27T17:44:05Z
dc.date.available2012-11-27T17:44:05Z
dc.date.issued2012-05
dc.date.submitted2010-07
dc.identifier.urihttp://hdl.handle.net/1721.1/75033
dc.description.abstractWe present a novel linear program for the approximation of the dynamic programming cost-to-go function in high-dimensional stochastic control problems. LP approaches to approximate DP have typically relied on a natural “projection” of a well-studied linear program for exact dynamic programming. Such programs restrict attention to approximations that are lower bounds to the optimal cost-to-go function. Our program—the “smoothed approximate linear program”—is distinct from such approaches and relaxes the restriction to lower bounding approximations in an appropriate fashion while remaining computationally tractable. Doing so appears to have several advantages: First, we demonstrate bounds on the quality of approximation to the optimal cost-to-go function afforded by our approach. These bounds are, in general, no worse than those available for extant LP approaches and for specific problem instances can be shown to be arbitrarily stronger. Second, experiments with our approach on a pair of challenging problems (the game of Tetris and a queueing network control problem) show that the approach outperforms the existing LP approach (which has previously been shown to be competitive with several ADP algorithms) by a substantial margin.en_US
dc.language.isoen_US
dc.publisherInstitute for Operations Research and the Management Sciences (INFORMS)en_US
dc.relation.isversionofhttp://dx.doi.org/ 10.1287/opre.1120.1044en_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.sourceMIT web domainen_US
dc.titleApproximate Dynamic Programming via a Smoothed Linear Programen_US
dc.typeArticleen_US
dc.identifier.citationDesai, V. V., V. F. Farias, and C. C. Moallemi. “Approximate Dynamic Programming via a Smoothed Linear Program.” Operations Research 60.3 (2012): 655–674.en_US
dc.contributor.departmentSloan School of Managementen_US
dc.contributor.mitauthorFarias, Vivek F.
dc.relation.journalOperations Researchen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsDesai, V. V.; Farias, V. F.; Moallemi, C. C.en
dc.identifier.orcidhttps://orcid.org/0000-0002-5856-9246
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record