An asymptotically optimal policy for finite support models in the multiarmed bandit problem (Q415624): Difference between revisions
From MaRDI portal
Created claim: Wikidata QID (P12): Q56675674, #quickstatements; #temporary_batch_1707303357582 |
Set profile property. |
||
| Property / MaRDI profile type | |||
| Property / MaRDI profile type: MaRDI publication profile / rank | |||
Normal rank | |||
Revision as of 00:11, 5 March 2024
scientific article
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | An asymptotically optimal policy for finite support models in the multiarmed bandit problem |
scientific article |
Statements
An asymptotically optimal policy for finite support models in the multiarmed bandit problem (English)
0 references
8 May 2012
0 references
bandit problems
0 references
finite-time regret
0 references
MED policy
0 references
convex optimization
0 references
