Kernel Value Function Approximation

Kernel Value Function Approximation is a value function approximation method that employs kernel-based functions to represent and generalize value estimates in reinforcement learning, distinguishing itself by leveraging reproducing kernel Hilbert spaces to capture nonlinear relationships in state or state-action spaces.

18

Publications

730

Citations

47

Authors

23

Institutions

Publications per year

2017–2026

6

Authors

47

  1. MS
    Masashi Sugiyama

    Tokyo Institute of Technology, Japan

    2 publications · 51 citations

    2

    h-index

  2. JP
    Jan Peters

    Technische Universität Darmstadt, Germany

    2 publications · 40 citations

    2

    h-index

  3. DP
    Doina Precup

    McGill University, Canada

    2 publications · 60 citations

    2

    h-index

  4. JP
    Joëlle Pineau

    McGill University, Canada

    2 publications · 60 citations

    2

    h-index

  5. CT
    Christopher Towell

    Tokyo Institute of Technology, Japan

    2 publications · 51 citations

    2

    h-index

1–5 of 47

Venues

  1. 2

    h-index

  2. arXiv (Cornell University)

    Repository · 2 publications · 40 citations

    2

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 17 citations

    1

    h-index

  4. 1

    h-index

  5. MPG.PuRe (Max Planck Society)

    Repository · 1 publications · 16 citations

    1

    h-index

1–5