A note on strategies for bandit problems with infinitely many arms

Kung-Yu Chen and Chien-Tai Lin

Metrika: International Journal for Theoretical and Applied Statistics, 2004, vol. 59, issue 2, 193-203

Abstract: A bandit problem consisting of a sequence of n choices (n→∞) from a number of infinitely many Bernoulli arms is considered. The parameters of Bernoulli arms are independent and identically distributed random variables from a common distribution F on the interval [0,1] and F is continuous with F(0)=0 and F(1)=1. The goal is to investigate the asymptotic expected failure rates of k-failure strategies, and obtain a lower bound for the expected failure proportion over all strategies presented in Berry et al. (1997). We show that the asymptotic expected failure rates of k-failure strategies when 0>b≤1 and a lower bound can be evaluated if the limit of the ratio F(1)−F(t) versus (1−t) b exists as t→1 − for some b>0. Copyright Springer-Verlag 2004

Keywords: k-failure strategy; m-run strategy; N n -learning strategy; non-recalling m-run strategy (search for similar items in EconPapers)
Date: 2004
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1007/s001840300279 (text/html)
Access to full text is restricted to subscribers.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:metrik:v:59:y:2004:i:2:p:193-203

Ordering information: This journal article can be ordered from
http://www.springer.com/statistics/journal/184/PS2

DOI: 10.1007/s001840300279

Access Statistics for this article

Metrika: International Journal for Theoretical and Applied Statistics is currently edited by U. Kamps and Norbert Henze

More articles in Metrika: International Journal for Theoretical and Applied Statistics from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().