Robust Value Iteration

Robust Value Iteration is a model-based reinforcement learning algorithm that extends the standard value iteration framework by incorporating uncertainty sets for transition probabilities, thereby optimizing policy performance under worst-case environmental dynamics within bounded deviations from nominal estimates.

6

Publications

105

Citations

20

Authors

8

Institutions

Publications per year

2017–2026

3

Authors

20

  1. KD
    Kenji Doya

    Okinawa Institute of Science and Technology Graduate University, Japan

    1 publications · 22 citations

    1

    h-index

  2. ZX
    Zuoxia Xing

    Shenyang University of Technology, China

    1 publications · 12 citations

    1

    h-index

  3. MM
    Mahdi Milani Fard

    McGill University, Canada

    1 publications · 10 citations

    1

    h-index

  4. HN
    Hideaki Nakao

    University of Michigan, United States

    1 publications · 16 citations

    1

    h-index

  5. DL
    David L. Kaufman

    University of Michigan, United States

    1 publications · 22 citations

    1

    h-index

1–5 of 20

Venues

  1. INFORMS journal on computing

    1 publications · 22 citations

    1

    h-index

  2. PolyPublie (École Polytechnique de Montréal)

    Repository · 1 publications · 10 citations

    1

    h-index

  3. International Conference on Artificial Intelligence and Statistics

    Conference · 1 publications · 22 citations

    1

    h-index

  4. International Conference on Machine Learning

    Conference · 1 publications · 23 citations

    1

    h-index

  5. Optimal Control Applications and Methods

    1 publications · 12 citations

    1

    h-index

1–5