Tsallis-INF: an optimal algorithm for stochastic and adversarial bandits (Q4998901)
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: Tsallis-INF: an optimal algorithm for stochastic and adversarial bandits |
scientific article; zbMATH DE number 7370545
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Tsallis-INF: an optimal algorithm for stochastic and adversarial bandits |
scientific article; zbMATH DE number 7370545 |
Statements
9 July 2021
0 references
bandits
0 references
online learning
0 references
best of both worlds
0 references
online mirror descent
0 references
Tsallis entropy
0 references
multi-armed bandits
0 references
stochastic
0 references
adversarial
0 references
I.I.D.
0 references
0.7904950976371765
0 references
0.7741712331771851
0 references
0.7681640386581421
0 references
0.7674009799957275
0 references
0.7644397616386414
0 references
