Nonparametric bandit methods (Q806690)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 4207247
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Nonparametric bandit methods |
scientific article; zbMATH DE number 4207247 |
Statements
Nonparametric bandit methods (English)
0 references
1991
0 references
The authors consider an infinite-horizon bandit problem within a nonparametric setting. Supposing K arms are available, each satisfying a probability bound, the sample plans proposed are shown to be asymptotically optimal and converge at guaranteed rates. In the bounded- arm case, the rate is optimal. Finally, the theory is extended to the case in which the bandit population is infinite.
0 references
infinite-horizon bandit problem
0 references
nonparametric setting
0 references
0 references
0 references
0.9016303
0 references
0.89648527
0 references
0 references
0.88065803
0 references
0.8803994
0 references
0.8771499
0 references
