Risk-Sensitive, Minimax, and Mixed Risk-Neutral/Minimax Control of Markov Decision Processes

dc.contributor.authorCoraluppi, Stephano P.en_US
dc.contributor.authorMarcus, Steven I.en_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T10:05:45Z
dc.date.available2007-05-23T10:05:45Z
dc.date.issued1998en_US
dc.description.abstractThis paper analyzes a connection between risk-sensitive and minimaxcriteria for discrete-time, finite-state Markov Decision Processes(MDPs). We synthesize optimal policies with respect to both criteria,both for finite horizon and discounted infinite horizon problems. Ageneralized decision-making framework is introduced, leading tostationary risk-sensitive and minimax optimal policies on theinfinite horizon with discounted costs.We introduce the mixed risk-neutral/minimaxobjective, and utilize results from risk-neutral and minimax controlto derive an information state process and dynamic programmingequations for the value function. We synthesize optimal control lawsboth on the finite and infinite horizon, and establish the effectivenessof the controller as a tool to trade off risk-neutral and minimaxobjectives.en_US
dc.format.extent258176 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5949
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1998-30en_US
dc.subjectstochastic systemsen_US
dc.subjectMarkov Decision Processesen_US
dc.subjectRisk-Sensitive Controlen_US
dc.subjectMinimax Controlen_US
dc.subjectIntelligent Control Systemsen_US
dc.titleRisk-Sensitive, Minimax, and Mixed Risk-Neutral/Minimax Control of Markov Decision Processesen_US
dc.typeTechnical Reporten_US

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
TR_98-30.pdf
Size:
252.13 KB
Format:
Adobe Portable Document Format