Concepedia

Batch Policy Iteration

Batch Policy Iteration is a reinforcement learning algorithm that, within the class of policy iteration methods, updates the policy using a fixed batch of data collected from prior interactions with the environment, thereby decoupling the data collection process from the policy improvement steps.

7

Publications

234

Citations

22

Authors

19

Institutions

Publications per year

2017–2026

4

Parents

Publications

7

High Confidence Policy Improvement

Philip S. Thomas, Georgios Theocharous, Mohammad Ghavamzadeh · International Conference on Machine Learning · 2015 · 96 citations

, , +16

Batch reinforcement learning approach using recursive feature elimination for network intrusion detection

Ankit Sharma, Manjeet Singh · Engineering Applications of Artificial Intelligence · 2024 · 39 citations

, , +15

Value-Iteration Based Fitted Policy Iteration: Learning with a Single Trajectory

András Antos, Csaba Szepesvári, Rémi Munos · 2007 · 30 citations · Full text

, , +16

A latent batch-constrained deep reinforcement learning approach for precision dosing clinical decision support

Xihe Qiu, Xiaoyu Tan, Qiong Li et al. · Knowledge-Based Systems · 2021 · 25 citations

, , +13

Towards Industrial Robot Learning from Demonstration

Wilson Ko, Yan Wu, Keng Peng Tee et al. · 2015 · 22 citations

, , +17

1–5 of 7

Authors

22

  1. CS
    Csaba Szepesvári

    University of Alberta, Canada

    2 publications · 41 citations

    2

    h-index

  2. YJ
    Yaochu Jin

    University of Surrey, United Kingdom

    1 publications · 25 citations

    1

    h-index

  3. PS
    Philip S. Thomas

    University of Massachusetts Amherst, United States

    1 publications · 96 citations

    1

    h-index

  4. AA
    András Antos

    Hungarian Academy of Sciences, Hungary

    1 publications · 30 citations

    1

    h-index

  5. HA
    Hoai An Le Thi

    Institut National des Sciences Appliquées Rouen Normandie, France

    1 publications · 11 citations

    1

    h-index

1–5 of 22

Institutions

19

  1. University of Alberta

    Edmonton, Canada

    2 h-index

    3 publications

    52 citations

  2. University of Massachusetts Amherst

    Amherst Center, United States

    1 h-index

    1 publications

    96 citations

  3. Adobe Systems (United States)

    San Jose, United States

    1 h-index

    2 publications

    192 citations

  4. Shanghai University of Engineering Science

    Shanghai, China

    1 h-index

    3 publications

    75 citations

  5. Université de Lille

    Lille, France

    1 h-index

    1 publications

    30 citations

  6. Beijing Jiaotong University

    Beijing, China

    1 h-index

    1 publications

    25 citations

  7. Hungarian Academy of Sciences

    Budapest, Hungary

    1 h-index

    2 publications

    60 citations

  8. Agency for Science, Technology and Research

    Singapore, Singapore

    1 h-index

    2 publications

    44 citations

1–8 of 19

Venues

  1. 1

    h-index

  2. Knowledge-Based Systems

    1 publications · 25 citations

    1

    h-index

  3. Journal of Global Optimization

    1 publications · 11 citations

    1

    h-index

  4. International Conference on Machine Learning

    Conference · 1 publications · 96 citations

    1

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 11 citations

    1

    h-index

1–5