Multi-armed bandits with discount factor near one: The Bernoulli case (Q1161450)
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: Multi-armed bandits with discount factor near one: The Bernoulli case |
scientific article; zbMATH DE number 3752619
| Language | Label | Description | Also known as |
|---|---|---|---|
| English | Multi-armed bandits with discount factor near one: The Bernoulli case |
scientific article; zbMATH DE number 3752619 |
Statements
Multi-armed bandits with discount factor near one: The Bernoulli case (English)
0 references
1981
0 references
Bernoulli bandit process
0 references
limit rule
0 references
play-the-winner rule
0 references
least failures rule
0 references
discount optimality
0 references
expected average reward optimality
0 references
multi-armed bandit
0 references
optimal arm pulling strategy
0 references
infinite sequence of Bernoulli random variables
0 references
Gittins index
0 references
asymptotic bounds
0 references
