Optimal exploration-exploitation in a multi-armed bandit problem with non-stationary rewards (Q5113912)
From MaRDI portal
!
This is the item page for this Wikibase entity, intended for internal use and editing purposes. Please use the normal view instead:
scientific article; zbMATH DE number 7213023
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Optimal exploration-exploitation in a multi-armed bandit problem with non-stationary rewards |
scientific article; zbMATH DE number 7213023 |
Statements
Optimal Exploration–Exploitation in a Multi-armed Bandit Problem with Non-stationary Rewards (English)
0 references
18 June 2020
0 references
multi-armed bandit
0 references
exploration/exploitation
0 references
nonstationary
0 references
dynamic oracle
0 references
minimax regret
0 references
dynamic regret
0 references
0.824036180973053
0 references
0.8149149417877197
0 references
0.8140532970428467
0 references
0.7958482503890991
0 references
0.784368097782135
0 references
