Batch Policy Optimization

Batch Policy Optimization is a reinforcement learning method that improves decision-making policies by optimizing over a fixed dataset of previously collected interactions, distinguishing itself from online approaches through its reliance on offline, batch-processed experience rather than real-time environment engagement.

7

Publications

510

Citations

24

Authors

13

Institutions

Publications per year

2017–2026

2

Variants

Offline Policy Optimization

Authors

24

  1. ME
    Mary E. Kurz

    Clemson University, United States

    1 publications · 14 citations

    1

    h-index

  2. PD
    Pierre-François Dutot

    Université Grenoble Alpes, France

    1 publications · 38 citations

    1

    h-index

  3. AD
    Asit Dan

    IBM (United States), United States

    1 publications · 401 citations

    1

    h-index

  4. JH
    Jiazhen Huo

    Tongji University, China

    1 publications · 15 citations

    1

    h-index

  5. DS
    Dale Schuurmans

    University of Alberta, Canada

    1 publications · 12 citations

    1

    h-index

1–5 of 24

Venues

  1. International Journal of Production Research

    1 publications · 18 citations

    1

    h-index

  2. Multimedia Systems

    1 publications · 401 citations

    1

    h-index

  3. Systems Engineering - Theory & Practice

    1 publications · 15 citations

    1

    h-index

  4. Neural Information Processing Systems

    Conference · 1 publications · 12 citations

    1

    h-index

  5. arXiv (Cornell University)

    Repository · 1 publications · 10 citations

1–5