Centralized Training

Centralized Training is a multi-robot learning framework in which a single, unified model or policy is trained using globally accessible information from all robots, distinguishing it from decentralized approaches by relying on a centralized data aggregation and update process.

170

Publications

8.5K

Citations

620

Authors

216

Institutions

Publications per year

2017–2026

164

Authors

620

  1. JL
    Jiawen Li

    South China University of Technology, China

    3 publications · 68 citations

    4

    h-index

  2. JK
    Joongheon Kim

    Korea University, South Korea

    4 publications · 338 citations

    4

    h-index

  3. HY
    Haipeng Yao

    Beijing University of Posts and Telecommunications, China

    4 publications · 207 citations

    4

    h-index

  4. HV
    H. Vincent Poor

    Princeton University, United States

    3 publications · 279 citations

    3

    h-index

  5. LL
    Lingjuan Lyu

    Sony Computer Science Laboratories, Japan

    3 publications · 699 citations

    3

    h-index

1–5 of 620

Venues

  1. arXiv (Cornell University)

    Repository · 19 publications · 997 citations

    16

    h-index

  2. IEEE Internet of Things Journal

    9 publications · 654 citations

    10

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 171 citations

    5

    h-index

  4. IEEE Access

    2 publications · 76 citations

    4

    h-index

  5. IEEE Transactions on Mobile Computing

    TMCCI · 2 publications · 83 citations

    4

    h-index

1–5