Multi-agent Policy Learning

Multi-Agent Policy Learning is a computational framework within reinforcement learning that models the simultaneous adaptation of decision-making strategies by multiple interacting agents in shared environments, distinguished by its focus on the emergence of joint policies through decentralized learning and strategic interdependence.

573

Publications

37.4K

Citations

1.9K

Authors

604

Institutions

Publications per year

2017–2026

440

Authors

1.9K

  1. SW
    Shimon Whiteson

    University of Oxford, United Kingdom

    9 publications · 1.1K citations

    9

    h-index

  2. DQ
    Dawei Qiu

    Imperial College London, United Kingdom

    8 publications · 638 citations

    8

    h-index

  3. JH
    Jianye Hao

    Tianjin University, China

    8 publications · 544 citations

    8

    h-index

  4. YY
    Yaodong Yang

    Peking University, China

    7 publications · 200 citations

    7

    h-index

  5. JL
    Jiawen Li

    South China University of Technology, China

    6 publications · 354 citations

    6

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 86 publications · 5.3K citations

    29

    h-index

  2. Applied Energy

    21 publications · 1.5K citations

    19

    h-index

  3. 13

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 13 publications · 708 citations

    12

    h-index

  5. IEEE Access

    11 publications · 722 citations

    10

    h-index

1–5