A minimax and asymptotically optimal algorithm for stochastic bandits (Q4645646)
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: A minimax and asymptotically optimal algorithm for stochastic bandits |
scientific article; zbMATH DE number 6999898
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | A minimax and asymptotically optimal algorithm for stochastic bandits |
scientific article; zbMATH DE number 6999898 |
Statements
10 January 2019
0 references
stochastic multi-armed bandits
0 references
regret analysis
0 references
upper confidence bound (UCB)
0 references
minimax optimality
0 references
asymptotic optimality
0 references
0.8435067534446716
0 references
0.8222958445549011
0 references
0.8052954077720642
0 references
0.7906786203384399
0 references
