Finite-state approximations for denumerable state discounted Markov decision processes (Q1085078)
From MaRDI portal
 | This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use this page instead for the normal view: Finite-state approximations for denumerable state discounted Markov decision processes |
scientific article; zbMATH DE number 3980961
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Finite-state approximations for denumerable state discounted Markov decision processes |
scientific article; zbMATH DE number 3980961 |
Statements
Finite-state approximations for denumerable state discounted Markov decision processes (English)
0 references
1986
0 references
The paper generalizes the finite-state interactive scheme of \textit{D. J. White} [in: Recent developments in Markov decision processes (1980; Zbl 0547.90064), and J. Math. Anal. Appl. 86, 292-306 (1982; Zbl 0533.90094)] to more general (denumerable) state sets and more general conditions of convergence. The rate of convergence is studied intensively and the asymptotic discount optimality of the policies generated by the algorithm is proved.
0 references
denumerable state discounted Markov decision processes
0 references
successive approximations
0 references
finite-state approximations
0 references
unbounded rewards
0 references
general conditions of convergence
0 references
rate of convergence
0 references
asymptotic discount optimality
0 references
0 references
0 references
