Exploration-exploitation policies with almost sure, arbitrarily slow growing asymptotic regret (Q5070864)
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: Exploration-exploitation policies with almost sure, arbitrarily slow growing asymptotic regret |
scientific article; zbMATH DE number 7507782
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Exploration-exploitation policies with almost sure, arbitrarily slow growing asymptotic regret |
scientific article; zbMATH DE number 7507782 |
Statements
EXPLORATION–EXPLOITATION POLICIES WITH ALMOST SURE, ARBITRARILY SLOW GROWING ASYMPTOTIC REGRET (English)
0 references
14 April 2022
0 references
bandits
0 references
forcing actions
0 references
inflated sample means
0 references
multi-armed
0 references
online learning
0 references
sequential allocation
0 references
upper confidence bounds
0 references
0 references
0.8084927201271057
0 references
0.7922816276550293
0 references
0.7800253629684448
0 references
0.7768810391426086
0 references
0.773647129535675
0 references
