An improved upper bound on the expected regret of UCB-type policies for a matching-selection bandit problem (Q1785430)
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: An improved upper bound on the expected regret of UCB-type policies for a matching-selection bandit problem |
scientific article; zbMATH DE number 6945410
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | An improved upper bound on the expected regret of UCB-type policies for a matching-selection bandit problem |
scientific article; zbMATH DE number 6945410 |
Statements
An improved upper bound on the expected regret of UCB-type policies for a matching-selection bandit problem (English)
0 references
28 September 2018
0 references
multi-armed bandit problem
0 references
matching
0 references
regret analysis
0 references
combinatorial bandit
0 references
online learning
0 references
0.7758748531341553
0 references
0.7266930341720581
0 references
0.7240365743637085
0 references
