Relative Value Iteration

Relative Value Iteration is a dynamic programming algorithm within the class of average reward reinforcement learning methods that iteratively updates value differences relative to a reference state to solve infinite-horizon Markov decision processes under the average reward criterion.

17

Publications

662

Citations

39

Authors

22

Institutions

Publications per year

2017–2026

7

Authors

39

  1. MT
    Meixia Tao

    Shanghai Jiao Tong University, China

    2 publications · 130 citations

    2

    h-index

  2. RC
    Rolando Cavazos–Cadena

    Universidad Autónoma Agraria Antonio Narro, Mexico

    2 publications · 23 citations

    2

    h-index

  3. RJ
    Rahul Jain

    University of Southern California, United States

    2 publications · 26 citations

    2

    h-index

  4. EF
    E. Fernández-Gaucherand

    University of Arizona, United States

    2 publications · 23 citations

    2

    h-index

  5. AG
    Abhishek Gupta

    University of Illinois Urbana-Champaign, United States

    2 publications · 26 citations

    2

    h-index

1–5 of 39

Venues

  1. IEEE Transactions on Wireless Communications

    2 publications · 145 citations

    2

    h-index

  2. Journal of Applied Probability

    JAP · 2 publications · 23 citations

    2

    h-index

  3. SIAM Journal on Control and Optimization

    2 publications · 254 citations

    2

    h-index

  4. 2021 IEEE Global Communications Conference (GLOBECOM)

    Conference · 1 publications · 41 citations

    1

    h-index

  5. China Communications

    1 publications · 26 citations

    1

    h-index

1–5