On the existence of fixed points for approximate value iteration and temporal-difference learning (Q1586803): Difference between revisions
From MaRDI portal
Removed claim: author (P16): Item:Q399882 |
Changed an Item |
||
| Property / author | |||
| Property / author: Benjamin van Roy / rank | |||
Normal rank | |||
Revision as of 03:55, 14 February 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | On the existence of fixed points for approximate value iteration and temporal-difference learning |
scientific article |
Statements
On the existence of fixed points for approximate value iteration and temporal-difference learning (English)
0 references
19 February 2001
0 references
dynamic programming
0 references
neurodynamic programming
0 references
reinforcement learning
0 references
temporal-difference learning
0 references
value iteration
0 references
