Sample-based Value Iteration

Sample-Based Value Iteration is a variant of the value iteration algorithm in reinforcement learning that belongs to the class of dynamic programming methods and is distinguished by its use of sampled transitions and rewards to approximate the Bellman update, thereby enabling scalable and model-free policy evaluation in large or stochastic environments.

2

Publications

29

Citations

6

Authors

2

Institutions

Publications per year

2017–2026

0

Authors

6

  1. MH
    M. Herzberg

    Tel Aviv University, Israel

    1 publications · 10 citations

    1

    h-index

  2. DJ
    Davy Janssens

    Hasselt University, Belgium

    1 publications · 19 citations

    1

    h-index

  3. GW
    Geert Wets

    Hasselt University, Belgium

    1 publications · 19 citations

    1

    h-index

  4. MV
    Marlies Vanhulsel

    Flemish Institute for Technological Research, Belgium

    1 publications · 19 citations

    1

    h-index

  5. KV
    Koen Vanhoof

    Hasselt University, Belgium

    1 publications · 19 citations

    1

    h-index

1–5 of 6

Venues

  1. Expert Systems with Applications

    1 publications · 19 citations

    1

    h-index

  2. European Journal of Operational Research

    1 publications · 10 citations

    1

    h-index

  3. Neurocomputing

    1 publications · 17 citations

1–3