Article ID: | iaor20002392 |
Country: | Germany |
Volume: | 49 |
Issue: | 3 |
Start Page Number: | 441 |
End Page Number: | 456 |
Publication Date: | Jan 1999 |
Journal: | Mathematical Methods of Operations Research (Heidelberg) |
Authors: | Cavazos-Cadena R., Montes-De-Oca R. |
Keywords: | markov processes |
This work concerns controlled Markov chains with denumerable state space and discrete time parameter. The reward function is assumed to be ≤ 0 and the performance of a control policy is measured by the expected total-reward criterion. Within this context, sufficient conditions are given so that the existence of a stationary policy which is ϵ-optimal at every state is guaranteed.