Accession Number : AD0777392
Title : Denumerable State Markov Decision Processes with Unbounded Costs.
Descriptive Note : Technical publication,
Corporate Author : NAVAL WEAPONS CENTER CHINA LAKE CALIF
Personal Author(s) : Reed,Frank C.
Report Date : MAR 1974
Pagination or Media Count : 63
Abstract : The report establishes sufficient conditions for both the existence of stationary optimal policies and the optimality of stationary policies in Markov decision processes with unbounded costs. The optimization criteria considered are minimum expected discounted cost over an infinite horizon and minimum expected average cost per unit time. Sufficient conditions that one may frequently establish in applications are given for the existence of a stationary optimal policy for both optimization criteria. (Modified author abstract)
Descriptors : *Decision theory, *Stochastic processes, Costs, Random variables, Theorems
Subject Categories : Operations Research
Distribution Statement : APPROVED FOR PUBLIC RELEASE