A variance minimization problem for a Markov decision process (Q1091952): Difference between revisions
From MaRDI portal
Removed claim: reviewed by (P1447): Item:Q731708 |
Changed an Item |
||
| Property / reviewed by | |||
| Property / reviewed by: Makiko Nisio / rank | |||
Normal rank | |||
Revision as of 15:27, 20 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A variance minimization problem for a Markov decision process |
scientific article |
Statements
A variance minimization problem for a Markov decision process (English)
0 references
1987
0 references
This paper deals with a discrete time Markov decision process with finite states and finite actions. The author investigates the problem to determine an optimal random policy that minimizes the variance of reward, with some constraint on the average reward. Introducing a parametric Markov decision process, he gives a procedure to find this optimal policy.
0 references
discrete time Markov decision process
0 references
finite states
0 references
finite actions
0 references
optimal random policy
0 references
variance of reward
0 references
parametric Markov decision process
0 references
