Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state (Q1194211): Difference between revisions
From MaRDI portal
Latest revision as of 10:45, 30 July 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state |
scientific article |
Statements
Existence of optimal stationary policies in average reward Markov decision processes with a recurrent state (English)
0 references
27 September 1992
0 references
This paper deals with discrete time average reward Markov decision processes with countable state space. Under some structural conditions the authors prove the existence of an optimal stationary policy, using renewal theory. Also the \(\liminf\) and the \(\limsup\) average optimal stationary policies are investigated.
0 references
recurrent state
0 references
discrete time average reward Markov decision processes
0 references
countable state space
0 references
existence of an optimal stationary policy
0 references
renewal theory
0 references
0 references
