Batch Reinforcement Learning

Batch Reinforcement Learning is a reinforcement learning paradigm in which the agent learns a policy exclusively from a fixed dataset of previously collected interactions, without further environment exploration.

153

Publications

11.1K

Citations

475

Authors

150

Institutions

Publications per year

2017–2026

94

Authors

475

  1. FR
    Frederik Ruelens

    KU Leuven, Belgium

    9 publications · 808 citations

    9

    h-index

  2. MR
    Marcello Restelli

    Politecnico di Milano, Italy

    7 publications · 301 citations

    7

    h-index

  3. BC
    Bert Claessens

    Flemish Institute for Technological Research, Belgium

    7 publications · 757 citations

    7

    h-index

  4. MR
    Martin Riedmiller

    University of Freiburg, Germany

    6 publications · 558 citations

    6

    h-index

  5. NJ
    Nan Jiang

    East China Jiaotong University, China

    5 publications · 177 citations

    5

    h-index

1–5 of 475

Venues

  1. arXiv (Cornell University)

    Repository · 43 publications · 3.1K citations

    23

    h-index

  2. Computers & Chemical Engineering

    6 publications · 580 citations

    6

    h-index

  3. 4

    h-index

  4. IEEE Transactions on Smart Grid

    4 publications · 721 citations

    4

    h-index

  5. Journal of Machine Learning Research

    JMLR · 3 publications · 276 citations

    3

    h-index

1–5