A note on maximal mean/standard deviation ratio in an undiscounted MDP (Q1823169)
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: A note on maximal mean/standard deviation ratio in an undiscounted MDP |
scientific article; zbMATH DE number 4114424
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A note on maximal mean/standard deviation ratio in an undiscounted MDP |
scientific article; zbMATH DE number 4114424 |
Statements
A note on maximal mean/standard deviation ratio in an undiscounted MDP (English)
0 references
1989
0 references
A stationary policy in an MDP (Markov decision process) induces a stationary probability distribution of the reward from each initial state. This note is related to the problem of maximizing the mean/standard deviation ratio of the stationary distribution. It concludes that a pure policy optimum exists.
0 references
undiscounted MDP
0 references
mean-variance
0 references
stationary policy
0 references
