Approximate Value Functions

Approximate Value Functions is a computational method in reinforcement learning that belongs to the class of value function estimation techniques, distinguished by its use of parametric function approximators to estimate the expected return of states or actions when exact computation is intractable.

281

Publications

30.6K

Citations

571

Authors

259

Institutions

Publications per year

2017–2026

75

Authors

571

  1. RM
    Rémi Munos

    Google (United States), United States

    7 publications · 650 citations

    7

    h-index

  2. RP
    Ronald Parr

    Duke University, United States

    6 publications · 820 citations

    6

    h-index

  3. CB
    Craig Boutilier

    University of Toronto, Canada

    6 publications · 285 citations

    6

    h-index

  4. SM
    Sridhar Mahadevan

    University of Massachusetts Amherst, United States

    6 publications · 268 citations

    6

    h-index

  5. DP
    Doina Precup

    McGill University, Canada

    5 publications · 290 citations

    5

    h-index

1–5 of 571

Venues

  1. arXiv (Cornell University)

    Repository · 23 publications · 1.4K citations

    17

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 3.6K citations

    6

    h-index

  3. PolyPublie (École Polytechnique de Montréal)

    Repository · 5 publications · 201 citations

    5

    h-index

  4. 5

    h-index

  5. International Conference on Machine Learning

    Conference · 4 publications · 175 citations

    4

    h-index

1–5