Show simple item record

dc.contributor.advisorFu, Michael C.en_US
dc.contributor.advisorMarcus, Steven I.en_US
dc.contributor.authorHe, Yingen_US
dc.contributor.authorFu, Michael C.en_US
dc.contributor.authorMarcus, Steven I.en_US
dc.date.accessioned2007-05-23T10:07:22Z
dc.date.available2007-05-23T10:07:22Z
dc.date.issued1999en_US
dc.identifier.urihttp://hdl.handle.net/1903/6029
dc.description.abstractIn this paper, we give a summary of recent development of simulation-based algorithmsfor average cost MDP problems, which are different from those for discounted cost problems or shortest pathproblems. We introduce both simulation-based policy iteration algorithms and simulation-based value iterationalgorithms for average cost problems, and give the pros and cons of each algorithm.en_US
dc.format.extent263703 bytes
dc.format.mimetypeapplication/pdf
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1999-56en_US
dc.subjectalgorithmsen_US
dc.subjectSimulation-Based Policy Iterationen_US
dc.subjectSimulation-Based Value Iterationen_US
dc.subjectMarkov Decision Processesen_US
dc.subjectaverage costen_US
dc.subjectUnichainen_US
dc.subjectSystems Integration Methodologyen_US
dc.titleSimulation-Based Algorithms for Average Cost Markov Decision Processesen_US
dc.typeTechnical Reporten_US
dc.contributor.departmentISRen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record