The Multi-Armed Bandit Problem: Decomposition and Computation

@article{Katehakis1987TheMB,
  title={The Multi-Armed Bandit Problem: Decomposition and Computation},
  author={M. Katehakis and A. F. Veinott},
  journal={Math. Oper. Res.},
  year={1987},
  volume={12},
  pages={262-268}
}
  • M. Katehakis, A. F. Veinott
  • Published 1987
  • Computer Science, Mathematics
  • Math. Oper. Res.
  • This paper is dedicated to our friend and mentor, Cyrus Derman, on the occasion of his 60th birthday. The multi-armed bandit problem arises in sequentially allocating effort to one of N projects and sequentially assigning patients to one of N treatments in clinical trials. Gittins and Jones Gittins, J. C., Jones, D. M. 1974. A dynamic allocation index for the sequential design of experiments. J. Gani, K. Sarkadi, L. Vince, eds. Progress in Statistics. European Meeting of Statisticians, 1972… CONTINUE READING
    Multiarmed Bandits and Gittins Index
    5
    The multi-armed bandit, with constraints
    15
    Q-Learning for Bandit Problems
    18
    Risk-Sensitive and Risk-Neutral Multiarmed Bandits
    19
    A Perpetual Search for Talent Across Overlapping Generations: A Learning Process
    A Generalized Gittins Index for a Class of Multiarmed Bandits with General Resource Requirements
    10

    References

    Publications referenced by this paper.
    SHOWING 1-7 OF 7 REFERENCES
    Linear Programming for Finite State Multi-Armed Bandit Problems
    22
    haaOit Processes and Dynamic Allocati < » i Indices
    • 1979
    19»)). Multi-Armed Bioidits and the Gittins Index
      A Note (» M N. Katdtakis, and Y.-R. Chen's OMnputation of the Gittins Index
      • 1986
      Extensimis of the Mnltiarmed Bandit Pn^km: The Discounted Case
        Introduction to Stodiastic Dynamic Progrtanming. Academic ftess
        • 1983