Batch Policy Learning

Batch Policy Learning is a category of reinforcement learning methods in which a policy is optimized using a fixed dataset collected from previously executed policies, without active environmental interaction during the learning process.

67

Publications

3.9K

Citations

216

Authors

85

Institutions

Publications per year

2017–2026

40

Authors

216

  1. MR
    Martin Riedmiller

    University of Freiburg, Germany

    4 publications · 460 citations

    4

    h-index

  2. CS
    Csaba Szepesvári

    University of Alberta, Canada

    3 publications · 190 citations

    3

    h-index

  3. AS
    Adith Swaminathan

    Cornell University, United States

    3 publications · 352 citations

    3

    h-index

  4. AA
    András Antos

    Hungarian Academy of Sciences, Hungary

    2 publications · 179 citations

    2

    h-index

  5. CF
    Changjie Fan

    NetEase (China), China

    2 publications · 28 citations

    2

    h-index

1–5 of 216

Venues

  1. arXiv (Cornell University)

    Repository · 19 publications · 798 citations

    15

    h-index

  2. Journal of Machine Learning Research

    JMLR · 3 publications · 276 citations

    3

    h-index

  3. International Conference on Artificial Intelligence and Statistics

    Conference · 2 publications · 31 citations

    2

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 30 citations

    2

    h-index

  5. HAL (Le Centre pour la Communication Scientifique Directe)

    Repository · 1 publications · 149 citations

    1

    h-index

1–5