Neural Value Function Approximation

Neural Value Function Approximation is a value function approximation method that employs artificial neural networks to model and generalize value estimates over states or state-action pairs, distinguishing it from tabular or linear function approximation approaches through its use of nonlinear, distributed representations.

33

Publications

1.3K

Citations

87

Authors

53

Institutions

Publications per year

2017–2026

16

Authors

87

  1. MR
    Martin Riedmiller

    University of Freiburg, Germany

    3 publications · 190 citations

    3

    h-index

  2. RC
    Rémi Coulom

    Université de Lille, France

    2 publications · 96 citations

    2

    h-index

  3. ZW
    Zhaoran Wang

    Princeton University, United States

    2 publications · 27 citations

    2

    h-index

  4. ZY
    Zhuoran Yang

    Princeton University, United States

    2 publications · 27 citations

    2

    h-index

  5. TG
    Thomas Gabel

    Osnabrück University, Germany

    2 publications · 98 citations

    2

    h-index

1–5 of 87

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 47 citations

    3

    h-index

  2. 2

    h-index

  3. Neurocomputing

    2 publications · 58 citations

    2

    h-index

  4. IEEE Transactions on Fuzzy Systems

    TFS · 1 publications · 26 citations

    1

    h-index

  5. SSRN Electronic Journal

    Repository · 1 publications · 12 citations

    1

    h-index

1–5