|
|||||
|
|
Nearly optimal stationary policies in negative dynamic programming |
|
| Authors: | Rolando Cavazos-Cadena Raúl Montes-De-Oca |
| Affiliation: | (1) Departmento de Estadı′stica y Cálculo, Universidad Autónoma Agraria Antonio Narro, Buenavista, Saltillo COAH 25315, México (e-mail: rcavazos@uaaan.mx), XX;(2) Departmento de Matemáticas, Universidad Autónoma Metropolitana-Iztapalapa, Avenida Michoacán y La Purı′sima s/n, Col. Vicentina, México D.F. 09340, México (e-mail: momr@xanum.uam.mx), XX |
| Abstract: | |
| Keywords: | : Markov decision processes expected total-reward criterion negative rewards uniformly ε -optimal stationary policies |
| 本文献已被 SpringerLink 等数据库收录！ | |