Markov-achievable payoffs for finite-horizon decision models. (Q1965904)
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: Markov-achievable payoffs for finite-horizon decision models. |
scientific article; zbMATH DE number 1409166
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Markov-achievable payoffs for finite-horizon decision models. |
scientific article; zbMATH DE number 1409166 |
Statements
Markov-achievable payoffs for finite-horizon decision models. (English)
0 references
1 March 2000
0 references
The paper investigates a problem of the decision making theory. The considered question is if the mean of the given payoff function evaluated under a permissible control can be achieved or even overcame using a permissible Markov control. Assuming payoff function based on recent state and on the \(n\)-th earlier decisions and states, the authors derived properties which are sufficient and necessary for the examined task.
0 references
Markov decision model
0 references
payoff function
0 references
Markov plan
0 references
0.9275494
0 references
0.89657336
0 references
0.89553815
0 references
0.8952397
0 references
0.8935769
0 references
0.8905645
0 references
