Action-dependent stopping times and Markov decision process with unbounded rewards (Q1158111)
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: Action-dependent stopping times and Markov decision process with unbounded rewards |
scientific article; zbMATH DE number 3739321
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Action-dependent stopping times and Markov decision process with unbounded rewards |
scientific article; zbMATH DE number 3739321 |
Statements
Action-dependent stopping times and Markov decision process with unbounded rewards (English)
0 references
1981
0 references
successive-approximation method
0 references
semi Markov decision processes
0 references
unbounded rewards
0 references
actions-dependent stopping time
0 references
algorithm
0 references
equal-row- sum property
0 references
lower bounds
0 references
elimination of non-optimal actions
0 references
upper bounds
0 references
0 references
0 references
0 references
