Discrete multiarmed bandits and multiparameter processes (Q1317211)
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 528195
| Language | Label | Description | Also known as |
|---|---|---|---|
| default for all languages | No label defined |
||
| English | Discrete multiarmed bandits and multiparameter processes |
scientific article; zbMATH DE number 528195 |
Statements
Discrete multiarmed bandits and multiparameter processes (English)
0 references
21 April 1994
0 references
The author reformulates the multiarmed bandit problem in discrete time as an optimal stochastic control problem for a multiparameter process. Within this framework, the dynamic allocation index, the so-called Gittins index, becomes a multiparameter process, and it is shown how it leads to optimal solutions. The main advantage of such an approach is that it provides a convenient and elegant representation of switching strategies by using the notion of optimal increasing paths or strategies over a partially ordered set.
0 references
multiarmed bandit problem
0 references
dynamic allocation index
0 references
Gittins index
0 references
switching strategies
0 references
0.866521954536438
0 references
0.8545243740081787
0 references
0.8545243740081787
0 references
0.8476237654685974
0 references
0.8434568047523499
0 references
