A forecast horizon and a stopping rule for general Markov decision processes (Q1104254)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 4055402
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A forecast horizon and a stopping rule for general Markov decision processes |
scientific article; zbMATH DE number 4055402 |
Statements
A forecast horizon and a stopping rule for general Markov decision processes (English)
0 references
1988
0 references
This paper presents conditions for the existence and detection of a forecast horizon for Markov decision processes with Borel state space. The conditions include the assumptions that the control set is finite and that there is a unique optimal stationary policy. The approach and results are closely related to other works in the area, e.g., \textit{K. Hinderer} and \textit{G. Hübner} [Information theory, statistical decision functions, random processes, Trans. 7th Prague Conf., Vol. A, Prague 1974, 245-257 (1977; Zbl 0416.90076)]; \textit{G. Hübner} [Bonn. Math. Schr. 98, 57-65 (1977; Zbl 0384.93041); Z. Angew. Math. Mech. 57, 477-480 (1977; Zbl 0368.90111)].
0 references
discounted and average reward criteria
0 references
existence and detection of a forecast horizon
0 references
Markov decision processes
0 references
Borel state space
0 references
unique optimal stationary policy
0 references
0 references
0.8653583526611328
0 references
0.8608038425445557
0 references
0.8335334062576294
0 references
0.8271932005882263
0 references
0.7974578738212585
0 references
