Risk-Sensitive and Minimax Control of Discrete-Time, Finite-State Markov Decision Processes

Simple item page
dc.contributor.authorCoraluppi, Stephano P.en_US
dc.contributor.authorMarcus, Steven I.en_US
dc.contributor.departmentISRen_US
dc.date.accessioned2007-05-23T10:05:44Z
dc.date.available2007-05-23T10:05:44Z
dc.date.issued1998en_US
dc.description.abstractThis paper analyzes a connection between risk-sensitive and minimaxcriteria for discrete-time, finite-states 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, which includes asspecial cases a number of approaches that have been considered in theliterature. The framework allows for discounted risk-sensitive andminimax formulations leading to stationary optimal policies on theinfinite horizon. We illustrate our results with a simple machinereplacement problem.en_US
dc.format.extent330629 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5948
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1998-29en_US
dc.subjectoptimal controlen_US
dc.subjectRisk-Sensitive Controlen_US
dc.subjectMinimax Controlen_US
dc.subjectMarkov Decision Processesen_US
dc.subjectIntelligent Control Systemsen_US
dc.titleRisk-Sensitive and Minimax Control of Discrete-Time, Finite-State Markov Decision Processesen_US
dc.typeTechnical Reporten_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
TR_98-29.pdf
Size:
322.88 KB
Format:
Adobe Portable Document Format
Download

Collections

Institute for Systems Research Technical Reports