Two-stage bandits (Q1115072): Difference between revisions

From MaRDI portal
Added link to MaRDI item.
Set OpenAlex properties.
 
(One intermediate revision by one other user not shown)
Property / MaRDI profile type
 
Property / MaRDI profile type: MaRDI publication profile / rank
 
Normal rank
Property / full work available at URL
 
Property / full work available at URL: https://doi.org/10.1214/aos/1176350841 / rank
 
Normal rank
Property / OpenAlex ID
 
Property / OpenAlex ID: W1992595769 / rank
 
Normal rank

Latest revision as of 22:17, 19 March 2024

scientific article
Language Label Description Also known as
English
Two-stage bandits
scientific article

    Statements

    Two-stage bandits (English)
    0 references
    0 references
    0 references
    1988
    0 references
    Two stochastic processes, or ``arms'', that yield dichotomous responses are available for use in a two-stage decision problem. During the first stage, arms are chosen sequentially; the resulting observations are discounted by a fixed value \(\beta\). A single arm must be used in the second stage, in which observations are not discounted. The decision to end the first stage is based on the data obtained. Optimal strategies are considered in the presence of the random discount sequence that arises in this setting. This extends the work of \textit{D. A. Berry} and \textit{B. Fristedt} [Ann. Stat. 7, 1086-1105 (1979; Zbl 0415.62056)].
    0 references
    two-stage bandit
    0 references
    sequential decisions
    0 references
    regular discounting
    0 references
    dichotomous responses
    0 references
    two-stage decision problem
    0 references
    Optimal strategies
    0 references
    random discount sequence
    0 references

    Identifiers