Concepedia

Stochastic Bandits

Stochastic Bandits is a sequential decision-making framework in which a learner repeatedly selects actions from a fixed set of alternatives and receives noisy reward feedback, with the defining characteristic that the rewards associated with each action are drawn independently from fixed but unknown probability distributions.

618

Publications

44.3K

Citations

940

Authors

373

Institutions

Publications per year

2017–2026

251

Variants

Stochastic Multi-armed Bandits

Parents

Publications

618

Finite-time Analysis of the Multiarmed Bandit Problem

Peter Auer, Nicolò Cesa‐Bianchi, Paul Fischer · Machine Learning · 2002 · 5.8K citations · Full text

, , +13

The Nonstochastic Multiarmed Bandit Problem

Peter Auer, Nicolò Cesa‐Bianchi, Yoav Freund et al. · SIAM Journal on Computing · 2002 · 2.3K citations

, , +12

Learning to rank

Zhe Cao, Tao Qin, Tie‐Yan Liu et al. · 2007 · 2K citations

, , +16

Bandit Processes and Dynamic Allocation Indices

John Gittins · Journal of the Royal Statistical Society Series B (Statistical Methodology) · 1979 · 1.5K citations

, , +11

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

Sébastien Bubeck · Foundations and Trends® in Machine Learning · 2012 · 1.2K citations

, , +14

1–5 of 618

Authors

940

  1. CS
    Csaba Szepesvári

    University of Alberta, Canada

    24 publications · 2.2K citations

    19

    h-index

  2. RM
    Rémi Munos

    Google (United States), United States

    16 publications · 1.5K citations

    15

    h-index

  3. BK
    Branislav Kveton

    Adobe Systems (United States), United States

    14 publications · 645 citations

    12

    h-index

  4. QZ
    Qing Zhao

    University of California, Davis, United States

    12 publications · 1.3K citations

    12

    h-index

  5. PA
    Peter Auer

    Montanuniversität Leoben, Austria

    12 publications · 3.1K citations

    11

    h-index

1–5 of 940

Institutions

373

  1. Massachusetts Institute of Technology

    Cambridge, United States

    20 h-index

    34 publications

    2K citations

  2. Cornell University

    Ithaca, United States

    19 h-index

    33 publications

    2.9K citations

  3. Centre National de la Recherche Scientifique

    Paris, France

    18 h-index

    32 publications

    1.9K citations

  4. Princeton University

    Princeton, United States

    18 h-index

    41 publications

    4.5K citations

  5. University of Alberta

    Edmonton, Canada

    17 h-index

    38 publications

    4.3K citations

  6. University of Southern California

    Los Angeles, United States

    15 h-index

    37 publications

    3.1K citations

  7. Institut national de recherche en sciences et technologies du numérique

    Le Chesnay-Rocquencourt, France

    14 h-index

    31 publications

    3K citations

  8. Stanford University

    Stanford, United States

    14 h-index

    24 publications

    2K citations

1–8 of 373

Venues

  1. arXiv (Cornell University)

    Repository · 166 publications · 7K citations

    42

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 14 publications · 419 citations

    13

    h-index

  3. IEEE Transactions on Automatic Control

    13 publications · 1.3K citations

    12

    h-index

  4. Advances in Applied Probability

    AAP · 14 publications · 1.2K citations

    12

    h-index

  5. Mathematics of Operations Research

    15 publications · 1.5K citations

    12

    h-index

1–5