Value iteration in countable state average cost Markov decision processes with unbounded costs (Q806687)
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: Value iteration in countable state average cost Markov decision processes with unbounded costs |
scientific article; zbMATH DE number 4207246
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Value iteration in countable state average cost Markov decision processes with unbounded costs |
scientific article; zbMATH DE number 4207246 |
Statements
Value iteration in countable state average cost Markov decision processes with unbounded costs (English)
0 references
1991
0 references
countable state Markov decision processes
0 references
finite action sets
0 references
unbounded costs
0 references
expected average cost optimal stationary policy
0 references
undiscounted value iteration
0 references
variable service rates
0 references
variable arrival parameter
0 references
0 references
0 references
0 references
