Discounted Dynamic Programming

Discounted Dynamic Programming is a dynamic programming framework in optimal control and reinforcement learning that computes the value function and optimal policy by iteratively applying the Bellman equation under a discounted reward criterion, distinguishing it from other dynamic programming methods through its explicit incorporation of a discount factor to weigh future rewards exponentially less than immediate ones.

64

Publications

4.6K

Citations

88

Authors

72

Institutions

Publications per year

2017–2026

4

Authors

88

  1. DP
    Dimitri P. Bertsekas

    Massachusetts Institute of Technology, United States

    4 publications · 206 citations

    4

    h-index

  2. HY
    Huizhen Yu

    Massachusetts Institute of Technology, United States

    3 publications · 156 citations

    3

    h-index

  3. AS
    Andrzej S. Nowak

    University of Zielona Góra, Poland

    3 publications · 77 citations

    3

    h-index

  4. DL
    Derong Liu

    Chinese Academy of Sciences, China

    3 publications · 140 citations

    3

    h-index

  5. DW
    Ding Wang

    Chinese Academy of Sciences, China

    3 publications · 140 citations

    3

    h-index

1–5 of 88

Venues

  1. Management Science

    5 publications · 578 citations

    5

    h-index

  2. Mathematics of Operations Research

    5 publications · 387 citations

    5

    h-index

  3. Economic Theory

    4 publications · 131 citations

    4

    h-index

  4. Operations Research Letters

    3 publications · 51 citations

    3

    h-index

  5. arXiv (Cornell University)

    Repository · 3 publications · 138 citations

    3

    h-index

1–5