Off-policy Learning

Off-Policy Learning is a reinforcement learning paradigm in which the agent learns the value function or policy of a target policy using data generated by a different behavioral policy, thereby enabling experience reuse and improved sample efficiency compared to on-policy methods.

465

Publications

39.4K

Citations

1.2K

Authors

329

Institutions

Publications per year

2017–2026

380

Authors

1.2K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    34 publications · 10.4K citations

    25

    h-index

  2. FL
    Frank L. Lewis

    The University of Texas at Arlington, United States

    27 publications · 3.7K citations

    24

    h-index

  3. RS
    Richard S. Sutton

    University of Alberta, Canada

    19 publications · 2.6K citations

    16

    h-index

  4. NH
    Nicolas Heess

    Google (United States), United States

    15 publications · 3.1K citations

    14

    h-index

  5. SG
    Shixiang Gu

    Google (United States), United States

    15 publications · 2.6K citations

    14

    h-index

1–5 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 198 publications · 16.7K citations

    54

    h-index

  2. 23

    h-index

  3. IEEE Transactions on Cybernetics

    18 publications · 1.7K citations

    16

    h-index

  4. International Conference on Machine Learning

    Conference · 13 publications · 1.1K citations

    12

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 10 publications · 486 citations

    10

    h-index

1–5