Concepedia

Reinforcement Learning

Reinforcement Learning is a machine learning paradigm in which an agent learns a policy for selecting actions in an environment so as to maximize expected cumulative reward, based on trial-and-error interaction with that environment and evaluative feedback in the form of scalar rewards.

33.1K

Publications

2.4M

Citations

62.6K

Authors

6.3K

Institutions

Publications per year

2017–2026

21.2K

Variants

Rl

Parents

Children

Publications

33.1K

Learning representations by back-propagating errors

David E. Rumelhart, Geoffrey E. Hinton, Ronald J. Williams · Nature · 1986 · 30.9K citations

, , +11

Human-level control through deep reinforcement learning

Volodymyr Mnih, Koray Kavukcuoglu, David Silver et al. · Nature · 2015 · 30K citations

, , +8

Reinforcement Learning: An Introduction

Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations

, , +12

Statistical Learning Theory

Yuhai Wu, Vladimir Vapnik · Technometrics · 1999 · 27K citations

, , +12

Reinforcement Learning: An Introduction

IEEE Transactions on Neural Networks · 2005 · 25.8K citations

, , +12

1–5 of 33.1K

Authors

62.6K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    275 publications · 47.6K citations

    92

    h-index

  2. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    207 publications · 45.8K citations

    84

    h-index

  3. DS
    David Silver

    Google DeepMind (United Kingdom), United Kingdom

    86 publications · 84.4K citations

    58

    h-index

  4. FL
    Frank L. Lewis

    The University of Texas at Arlington, United States

    124 publications · 17.5K citations

    58

    h-index

  5. PS
    Peter Stone

    The University of Texas at Austin, United States

    131 publications · 11.2K citations

    54

    h-index

1–5 of 62.6K

Institutions

6.3K

  1. University of California, Berkeley

    Berkeley, United States

    124 h-index

    1.7K publications

    206.5K citations

  2. Carnegie Mellon University

    Pittsburgh, United States

    114 h-index

    1.4K publications

    170.9K citations

  3. Massachusetts Institute of Technology

    Cambridge, United States

    107 h-index

    1.1K publications

    95.7K citations

  4. Google (United States)

    Mountain View, United States

    106 h-index

    1.8K publications

    326.8K citations

  5. Stanford University

    Stanford, United States

    105 h-index

    1K publications

    98.1K citations

  6. Tsinghua University

    Beijing, China

    102 h-index

    1.8K publications

    112.8K citations

  7. Princeton University

    Princeton, United States

    91 h-index

    586 publications

    50.1K citations

  8. University College London

    London, United Kingdom

    88 h-index

    654 publications

    106.2K citations

1–8 of 6.3K

Venues

  1. arXiv (Cornell University)

    Repository · 4K publications · 301.7K citations

    212

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 552 publications · 40.5K citations

    88

    h-index

  3. 87

    h-index

  4. IEEE Transactions on Vehicular Technology

    295 publications · 24.4K citations

    82

    h-index

  5. IEEE Internet of Things Journal

    312 publications · 23K citations

    82

    h-index

1–5