Average Reward Linear Programming

Average Reward Linear Programming is a mathematical optimization framework within the domain of Markov decision processes that characterizes the long-run expected reward per unit time through linear programming formulations, distinguishing itself by enabling the computation of optimal stationary policies under ergodicity assumptions.

17

Publications

727

Citations

34

Authors

30

Institutions

Publications per year

2017–2026

4

Authors

34

  1. LC
    L. C. M. Kallenberg

    Leiden University, Netherlands

    2 publications · 88 citations

    2

    h-index

  2. EA
    Eugene A. Feinberg

    Stony Brook University, United States

    2 publications · 118 citations

    2

    h-index

  3. JG
    Juan González Hernández

    Universidad de Granada, Spain

    1 publications · 61 citations

    1

    h-index

  4. VG
    Vicenç Gómez

    Universitat Pompeu Fabra, Spain

    1 publications · 98 citations

    1

    h-index

  5. TR
    Tomasz R. Bielecki

    Illinois Institute of Technology, United States

    1 publications · 71 citations

    1

    h-index

1–5 of 34

Venues

  1. Mathematics of Operations Research

    2 publications · 54 citations

    2

    h-index

  2. Mathematical Methods of Operations Research

    2 publications · 146 citations

    2

    h-index

  3. SIAM Journal on Control and Optimization

    2 publications · 89 citations

    2

    h-index

  4. IEEE Open Journal of Vehicular Technology

    OJVT · 1 publications · 72 citations

    1

    h-index

  5. arXiv (Cornell University)

    Repository · 1 publications · 98 citations

    1

    h-index

1–5