Constrained Multi-agent Reinforcement Learning

Constrained Multi-Agent Reinforcement Learning is a formal framework within multi-agent reinforcement learning that extends the standard Markov decision process to concurrent, interacting agents subject to shared constraints on cumulative costs, thereby distinguishing itself by enforcing joint policy optimization under both performance objectives and resource or safety limitations.

16

Publications

658

Citations

40

Authors

18

Institutions

Publications per year

2017–2026

15

Authors

40

  1. HZ
    Haifeng Zhou

    Pusan National University, South Korea

    1 publications · 19 citations

    1

    h-index

  2. AU
    Aditya Undurti

    American Institute of Aeronautics and Astronautics, United States

    1 publications · 14 citations

    1

    h-index

  3. MZ
    Meng Zhang

    Jiangsu University, China

    1 publications · 19 citations

    1

    h-index

  4. JA
    Jianping An

    Beijing Institute of Technology, China

    1 publications · 63 citations

    1

    h-index

  5. MZ
    Mustafa Z. Yousif

    Pusan National University, South Korea

    1 publications · 19 citations

    1

    h-index

1–5 of 40

Venues

  1. 2

    h-index

  2. IEEE Transactions on Vehicular Technology

    1 publications · 153 citations

    1

    h-index

  3. arXiv (Cornell University)

    Repository · 1 publications · 16 citations

    1

    h-index

  4. Journal of Fluid Mechanics

    1 publications · 19 citations

    1

    h-index

  5. 1

    h-index

1–5