Index-based policies for discounted multi-armed bandits on parallel machines. (Q1872472)
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: Index-based policies for discounted multi-armed bandits on parallel machines. |
scientific article; zbMATH DE number 1906256
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Index-based policies for discounted multi-armed bandits on parallel machines. |
scientific article; zbMATH DE number 1906256 |
Statements
Index-based policies for discounted multi-armed bandits on parallel machines. (English)
0 references
6 May 2003
0 references
Average-overtaking optimal
0 references
average-reward optimal
0 references
Gittins index
0 references
multi-armed bandit problem
0 references
parallel machines
0 references
suboptimality bound
0 references
0 references
0.9011147
0 references
0.89578307
0 references
0.8941473
0 references
0.88323915
0 references
0.88070375
0 references
