Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards (Q2788426)
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: Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards |
scientific article; zbMATH DE number 6542870
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards |
scientific article; zbMATH DE number 6542870 |
Statements
19 February 2016
0 references
stochastic bandit
0 references
finite-time regret
0 references
large deviation principle
0 references
Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards (English)
0 references
