Concepedia

Contextual Bandits

Contextual Bandits is a reinforcement learning framework in which an agent sequentially selects actions based on observed contextual information to maximize cumulative rewards, distinguished from multi-armed bandits by incorporating context-dependent action policies.

319

Publications

19.2K

Citations

722

Authors

230

Institutions

Publications per year

2017–2026

212

Variants

Contextual Multi-armed Bandits

Parents

Publications

319

A contextual-bandit approach to personalized news article recommendation

Lihong Li, Wei Chu, John Langford et al. · 2010 · 2.5K citations · Full text

, , +16

Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems

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

, , +14

Contextual bandits with linear Payoff functions

Wei Chu, Lihong Li, Lev Reyzin et al. · 2011 · 580 citations

, , +17

Thompson Sampling for Contextual Bandits with Linear Payoffs

Shipra Agrawal, Navin Goyal · arXiv (Cornell University) · 2012 · 548 citations · Full text

, , +17

Unbiased offline evaluation of contextual-bandit-based news article recommendation algorithms

Lihong Li, Wei Chu, John Langford et al. · 2011 · 464 citations · Full text

, , +13

1–5 of 319

Authors

722

  1. JL
    John Langford

    Microsoft (United States), United States

    26 publications · 5.2K citations

    21

    h-index

  2. LL
    Lihong Li

    Microsoft (United States), United States

    15 publications · 3.8K citations

    14

    h-index

  3. AA
    Alekh Agarwal

    Microsoft (United States), United States

    14 publications · 852 citations

    12

    h-index

  4. DB
    Djallel Bouneffouf

    IBM (United States), United States

    14 publications · 656 citations

    11

    h-index

  5. RE
    Robert E. Schapire

    AT&T (United States), United States

    11 publications · 3.8K citations

    11

    h-index

1–5 of 722

Institutions

230

  1. Microsoft (United States)

    Redmond, United States

    20 h-index

    62 publications

    3.7K citations

  2. Cornell University

    Ithaca, United States

    16 h-index

    26 publications

    873 citations

  3. Stanford University

    Stanford, United States

    13 h-index

    27 publications

    758 citations

  4. University of Pennsylvania

    Philadelphia, United States

    11 h-index

    24 publications

    1.9K citations

  5. University of Southern California

    Los Angeles, United States

    11 h-index

    23 publications

    682 citations

  6. Yahoo (United States)

    Sunnyvale, United States

    11 h-index

    24 publications

    11.6K citations

  7. Google (United States)

    Mountain View, United States

    10 h-index

    15 publications

    397 citations

  8. Massachusetts Institute of Technology

    Cambridge, United States

    10 h-index

    17 publications

    434 citations

1–8 of 230

Venues

  1. arXiv (Cornell University)

    Repository · 112 publications · 5.3K citations

    35

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 15 publications · 392 citations

    13

    h-index

  3. Neural Information Processing Systems

    Conference · 9 publications · 323 citations

    9

    h-index

  4. Conference on Learning Theory

    Conference · 6 publications · 208 citations

    6

    h-index

  5. International Conference on Machine Learning

    Conference · 6 publications · 144 citations

    6

    h-index

1–5