Exploration-exploitation tradeoff using variance estimates in multi-armed bandits (Q1017665)
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: Exploration-exploitation tradeoff using variance estimates in multi-armed bandits |
scientific article; zbMATH DE number 5552995
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Exploration-exploitation tradeoff using variance estimates in multi-armed bandits |
scientific article; zbMATH DE number 5552995 |
Statements
Exploration-exploitation tradeoff using variance estimates in multi-armed bandits (English)
0 references
12 May 2009
0 references
exploration-exploitation tradeoff
0 references
multi-armed bandits
0 references
Bernstein's inequality
0 references
high-probability bound
0 references
risk analysis
0 references
0 references
0.9281293153762816
0 references
0.8128303289413452
0 references
0.8116393685340881
0 references
0.8007463216781616
0 references
0.7891565561294556
0 references
