The Bellman's principle of optimality in the discounted dynamic programming (Q1112737)
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: The Bellman's principle of optimality in the discounted dynamic programming |
scientific article; zbMATH DE number 4079190
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | The Bellman's principle of optimality in the discounted dynamic programming |
scientific article; zbMATH DE number 4079190 |
Statements
The Bellman's principle of optimality in the discounted dynamic programming (English)
0 references
1987
0 references
The author presents a short proof of Bellman's optimality principle in discounted dynamic programming, which states that the policy \(\pi\) is optimal if and only if its reward I(\(\pi)\) satisfies the optimality equation. The given proof is based on the properties of the conditional expectation. Some further applications of the author's technique are proposed.
0 references
Bellman's optimality principle
0 references
discounted dynamic programming
0 references
0.92682356
0 references
0.90083057
0 references
0.8902675
0 references
0.8864271
0 references
0.88102573
0 references
0.87720436
0 references
0.87638265
0 references
