Show simple item record

dc.contributor.authorZang, Pengen_US
dc.date.accessioned2012-02-17T19:25:30Z
dc.date.available2012-02-17T19:25:30Z
dc.date.issued2011-11-14en_US
dc.identifier.urihttp://hdl.handle.net/1853/42906
dc.description.abstractThe Markov Decision Problem (MDP) is a widely applied mathematical model useful for describing a wide array of real world decision problems ranging from navigation to scheduling to robotics. Existing methods for solving MDPs scale poorly when applied to large domains where there are many components and factors to consider. In this dissertation, I study the use of non-tabular representations and human input as scaling techniques. I will show that the joint approach has desirable optimality and convergence guarantees, and demonstrates several orders of magnitude speedup over conventional tabular methods. Empirical studies of speedup were performed using several domains including a clone of the classic video game, Super Mario Bros. In the course of this work, I will address several issues including: how approximate representations can be used without losing convergence and optimality properties, how human input can be solicited to maximize speedup and user engagement, and how that input should be used so as to insulate against possible errors.en_US
dc.publisherGeorgia Institute of Technologyen_US
dc.subjectReinforcement learningen_US
dc.subjectMachine learningen_US
dc.subjectPlanningen_US
dc.subjectArtificial intelligenceen_US
dc.subjectMarkov decision processesen_US
dc.subject.lcshMarkov processes
dc.subject.lcshMathematical models
dc.subject.lcshDynamic programming
dc.titleScaling solutions to Markov Decision Problemsen_US
dc.typeDissertationen_US
dc.description.degreePhDen_US
dc.contributor.departmentComputingen_US
dc.description.advisorCommittee Chair: Charles Isbell; Committee Member: Alexander Gray; Committee Member: Andrea Thomaz; Committee Member: Michael Littman; Committee Member: Mike Stilmanen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record