Exact finite approximations of average-cost countable Markov Decision Processes

Simple item page
dc.creatorLeizarowitz, Arie
dc.creatorShwartz, Adam
dc.date2007-11-14
dc.date.accessioned2026-07-07T08:42:55Z
dc.date.available2026-07-07T08:42:55Z
dc.descriptionFor a countable-state Markov decision process we introduce an embedding which produces a finite-state Markov decision process. The finite-state embedded process has the same optimal cost, and moreover, it has the same dynamics as the original process when restricting to the approximating set. The embedded process can be used as an approximation which, being finite, is more convenient for computation and implementation.
dc.descriptionSubmitted to Automatica
dc.identifierhttps://arxiv.org/abs/0711.2185
dc.identifierhttp://arxiv.org/abs/0711.2185
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/142136
dc.subjectProbability
dc.subjectOptimization and Control
dc.subject90c40
dc.titleExact finite approximations of average-cost countable Markov Decision Processes
dc.typetext

Files

Collections

arXiv