Off-policy Value Estimation

Off-Policy Value Estimation is a method in reinforcement learning that estimates the expected return of a target policy using data generated by a different behavioral policy, thereby enabling evaluation without requiring environment interaction under the target policy.

28

Publications

1.2K

Citations

60

Authors

33

Institutions

Publications per year

2017–2026

18

Authors

60

  1. NK
    Nathan Kallus

    Cornell University, United States

    5 publications · 181 citations

    5

    h-index

  2. ON
    Ofir Nachum

    Google (United States), United States

    5 publications · 170 citations

    5

    h-index

  3. CS
    Csaba Szepesvári

    University of Alberta, Canada

    4 publications · 99 citations

    4

    h-index

  4. YC
    Yinlam Chow

    Google (United States), United States

    4 publications · 155 citations

    4

    h-index

  5. BD
    Bo Dai

    Georgia Institute of Technology, United States

    3 publications · 143 citations

    3

    h-index

1–5 of 60

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 473 citations

    12

    h-index

  2. International Conference on Machine Learning

    Conference · 2 publications · 27 citations

    2

    h-index

  3. Operations Research

    2 publications · 80 citations

    2

    h-index

  4. Machine Learning

    1 publications · 26 citations

    1

    h-index

  5. Open Repository and Bibliography (University of Liège)

    Repository · 1 publications · 16 citations

    1

    h-index

1–5