Skip to main content
SpringerLink
Log in

A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions

  • Notes
  • Published:
Statistical Papers Aims and scope Submit manuscript

Abstract

A bandit problem with infinitely many Bernoulli arms is considered. The parameters of Bernoulli arms are independent and identically distributed random variables from a generalized beta distributionG3B(a, b, λ) witha, b>0 and 0<λ<2. Under the generalized beta prior distributions, we first derive the asymptotic expected failure rates ofk-failure strategies, and then obtain a lower bound for the expected failure rate over all strategies investigated in Berry et al. (1997). The asymptotic expected failure rates for the other three strategies studied in Berry et al. (1997) are also included. Numerical estimations for a variety of generalized beta prior distributions are presented to illustrate the performances of these strategies.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Banks, J. S., Sundaram, R. K. (1992) Denumerable-armed bandits.Econometrica 60, 1071–1096

    Article  MATH  MathSciNet  Google Scholar 

  • Berry, D. A., Chen, R. W., Zame, A, Heath, D. C., Shepp, L. A. (1997) Bandit problems with infinitely many arms.Ann. Statist. 25, 2103–2116

    Article  MATH  MathSciNet  Google Scholar 

  • Berry, D. A., Fristedt, B. (1985)Bandit Problems: Sequential Allocations of Experiments. Chapman and Hall, London

    Google Scholar 

  • Chen, J. J., Novick, M. R. (1984) Bayesian analysis for Binomial models with generalized Beta prior distributions.J. Educ. Statist. 9, 163–175

    Article  Google Scholar 

  • Gittins, J. C. (1989)Multi-armed Bandit Allocation Indices. John Wiley & Sons, New York

    MATH  Google Scholar 

  • Herschkorn, S. J., Pekoz, E., Ross, S. M. (1996) Policies without memory for the infinite-armed Bernoulli bandit under the average-reward criterion.Probab. Engrg. Inform. Sci. 10, 21–28

    Article  MATH  MathSciNet  Google Scholar 

  • Libby, D. L., Novick, M. R. (1982) Multivariate generalized beta distributions with applications to utility assessment.J. Educ. Statist. 7, 271–294

    Article  Google Scholar 

  • Lin, C. T., Shiau, C. J. (2000) Some optimal strategies for bandit problems with Beta prior distributions.Ann. Inst. Statist. Math. 52, 397–405

    Article  MATH  MathSciNet  Google Scholar 

  • Pham-Gia, T., Duong, Q. P. (1989) The generalized Beta- and F-distributions in statistical modelling.Mathl Comput. Modelling 12, 1613–1625

    Article  MATH  MathSciNet  Google Scholar 

  • Robbins, H. (1952) Some aspects of the sequential design of experiments.Bull. Amer. Math. Soc. 58, 527–536

    Article  MATH  MathSciNet  Google Scholar 

  • Whittle, P. (1982),Optimization over Time 1. John Wiley & Sons, New York

    MATH  Google Scholar 

  • Whittle, P. (1983)Optimization over Time 2. John Wiley & Sons, New York

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Mathematics, Tmkang University, 251, Tamsui, Taiwan

    Kung-Yu Chen & Chien-Tai Lin

Authors
  1. Kung-Yu Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chien-Tai Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Chen, KY., Lin, CT. A note on infinite-armed Bernoulli bandit problems with generalized beta prior distributions. Statistical Papers 46, 129–140 (2005). https://doi.org/10.1007/BF02762039

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02762039

Key Words

Search

Navigation