Value Functions

Value Function is a real-valued function that assigns to each state (or state-action pair) the expected cumulative reward an agent can achieve from that point onward under a given policy, distinguishing it from other solution concepts in Markov Decision Processes by representing long-term desirability rather than immediate reward or action selection.

1.4K

Publications

126.9K

Citations

2.7K

Authors

882

Institutions

Publications per year

2017–2026

485

Authors

2.7K

  1. RM
    Rémi Munos

    Google (United States), United States

    21 publications · 2.4K citations

    18

    h-index

  2. DP
    Doina Precup

    McGill University, Canada

    22 publications · 5.1K citations

    17

    h-index

  3. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    16 publications · 1.2K citations

    15

    h-index

  4. RS
    Richard S. Sutton

    University of Alberta, Canada

    16 publications · 10.1K citations

    15

    h-index

  5. WD
    Will Dabney

    Google (United States), United States

    15 publications · 2K citations

    13

    h-index

1–5 of 2.7K

Venues

  1. arXiv (Cornell University)

    Repository · 201 publications · 21.2K citations

    62

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 36 publications · 2.4K citations

    21

    h-index

  3. Journal of Artificial Intelligence Research

    JAIR · 17 publications · 13.4K citations

    16

    h-index

  4. European Journal of Operational Research

    15 publications · 1.2K citations

    14

    h-index

  5. Mathematics of Operations Research

    16 publications · 642 citations

    14

    h-index

1–5