A polynomial time bound for Howard's policy improvement algorithm (Q1079511): Difference between revisions
From MaRDI portal
Added link to MaRDI item. |
Removed claim: author (P16): Item:Q803049 |
||
| Property / author | |||
| Property / author: Ulrich D. Holzbaur / rank | |||
Revision as of 03:32, 21 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | A polynomial time bound for Howard's policy improvement algorithm |
scientific article |
Statements
A polynomial time bound for Howard's policy improvement algorithm (English)
0 references
1986
0 references
discounted Markovian Decision Process
0 references
finite state and action space
0 references
Howard's policy improvement
0 references
optimal policy
0 references
