Mean-variance criteria in an undiscounted Markov decision process (Q1310718)
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: Mean-variance criteria in an undiscounted Markov decision process |
scientific article; zbMATH DE number 482365
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Mean-variance criteria in an undiscounted Markov decision process |
scientific article; zbMATH DE number 482365 |
Statements
Mean-variance criteria in an undiscounted Markov decision process (English)
0 references
1 November 1994
0 references
The author considers a discrete time Markov decision process with finite state and action sets. The goal is to minimize the variance of steady- state rewards subject to the constraint that average rewards per unit time are not less than a given number. An algorithm for the solution of this problem is formulated.
0 references
mean
0 references
finite state and action sets
0 references
variance
0 references
