KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints (Q6301530)
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: KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints |
preprint article from arXiv
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | KL-UCB-switch: optimal regret bounds for stochastic bandits from both a distribution-dependent and a distribution-free viewpoints |
preprint article from arXiv |
Statements
14 May 2018
0 references
stat.ML
0 references
cs.LG
0 references
math.ST
0 references
stat.TH
0 references
Aurélien Garivier
0 references
Hédi Hadiji
0 references
Pierre Menard
0 references
Gilles Stoltz
0 references
