Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state |
| |
Authors: | Rolando Cavazos-Cadena |
| |
Institution: | (1) Departamento de Estadistica y Cálculo, Universidad Autónoma Agraria Antonio Narro, Buenavista 25315, Saltillo, COAH, México;(2) Department of Mathematics, Texas Technical University, 79409 Lubbock, TX, USA |
| |
Abstract: | We consider discrete-timeaverage reward Markov decision processes with denumerable state space andbounded reward function. Under structural restrictions on the model the existence of an optimal stationary policy is proved; both the lim inf and lim sup average criteria are considered. In contrast to the usual approach our results donot rely on the average regard optimality equation. Rather, the arguments are based on well-known facts fromRenewal Theory.This research was supported in part by the Consejo Nacional de Ciencia y Tecnologia (CONACYT) under Grants PCEXCNA 040640 and 050156, and by SEMAC under Grant 89-1/00ifn$. |
| |
Keywords: | Average reward criteria Optimal stationary policies Recurrent state Renewal processes |
本文献已被 SpringerLink 等数据库收录! |
|