Picking the Best Expert from a Sequence

  • Ruth Bergman
  • Ronald L. Rivest
Part of the Lecture Notes in Statistics book series (LNS, volume 112)


We examine the problem of finding a good expert from a sequence of experts. Each expert has an “error rate”; we wish to find an expert with a low error rate. However, each expert’s error rate is unknown and can only be estimated by a sequence of experimental trials. Moreover, the distribution of error rates is also unknown. Given a bound on the total number of trials, there is thus a tradeoff between the number of experts examined and the accuracy of estimating their error rates.

We present a new expert-finding algorithm and prove an upper bound on the expected error rate of the expert found. A second approach, based on the sequential ratio test, gives another expert-finding algorithm that is not provably better but which performs better in our empirical studies.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [Drescher 89]
    Drescher, G. L. (1989), Made-Up Minds: A Constructivist Approach to Artificial Intelligence, PhD thesis, MIT.Google Scholar
  2. [Holland 85]
    Holland, J. H. (1985), Properties of the bucket brigade algorithm, in ‘First International Conference on Genetic Algorithms and Their Applications’, Pittsburg, PA, pp. 1–7.Google Scholar
  3. [Kaelbling 90]
    Kaelbling, L. P. (1990), Learning in Embedded Systems, Technical Report TR-90–04, Teleos Research.Google Scholar
  4. [Laird et al. 87]
    Laird, J. E., Newell, A. and Rosenbloom, P. S. (1978), ‘SOAR: An Architecture for General Intelligence’, Artificial Intelligence 33, 1–64.CrossRefGoogle Scholar
  5. [Rice 88]
    Rice, J. A. (1988), Mathematical Statistics and Data Analysis, Wadsworth & Brooks/Cole, Pacific Grove, CA.zbMATHGoogle Scholar
  6. [Sutton 90]
    Sutton, R. S. (1990), First Results with DYNA, an Integrated Architecture for Learning, Planning, and Reacting, in ‘Proceedings, AAAI-90’, Cambridge, Massachusetts.Google Scholar
  7. [Sutton 91]
    Sutton, R. S. (1991), Reinforcement Learning Architectures for Animats, in ‘First International Conference on Simulation of Adaptive Behavior’, The MIT Press, Cambridge, MA.Google Scholar
  8. [Wald 47]
    Wald, A. (1947), Sequential Analysis, John Wiley & Sons, Inc., Chapman & Hall, LTD., London.zbMATHGoogle Scholar
  9. [Watkins 89]
    Watkins, C. (1989), Learning from Delayed Rewards, PhD thesis, King’s College.Google Scholar

Copyright information

© Springer-Verlag New York, Inc. 1996

Authors and Affiliations

  • Ruth Bergman
    • 1
  • Ronald L. Rivest
    • 2
  1. 1.Artificial Intelligence LaboratoryMassachusetts Institute of TechnologyCambridgeUSA
  2. 2.Laboratory for Computer ScienceMassachusetts Institute of TechnologyCambridgeUSA

Personalised recommendations