Dynamics Model Learning

Dynamics Model Learning is a methodological framework within self-supervised robot learning that entails the acquisition of a predictive model of a system's temporal evolution by identifying the underlying transition rules that govern how states change in response to actions, distinguished from other modeling approaches by its focus on capturing the intrinsic physical or abstract dynamics without reliance on external supervision.

166

Publications

8.8K

Citations

509

Authors

162

Institutions

Publications per year

2017–2026

116

Authors

509

  1. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    12 publications · 1.3K citations

    11

    h-index

  2. JW
    Jiajun Wu

    Massachusetts Institute of Technology, United States

    10 publications · 559 citations

    10

    h-index

  3. SL
    Sergey Levine

    University of California, Berkeley, United States

    10 publications · 1.2K citations

    10

    h-index

  4. JB
    Joshua B. Tenenbaum

    Massachusetts Institute of Technology, United States

    8 publications · 438 citations

    8

    h-index

  5. JP
    Jan Peters

    Technische Universität Darmstadt, Germany

    6 publications · 352 citations

    6

    h-index

1–5 of 509

Venues

  1. arXiv (Cornell University)

    Repository · 59 publications · 2.9K citations

    28

    h-index

  2. IEEE Robotics and Automation Letters

    4 publications · 269 citations

    4

    h-index

  3. 2

    h-index

  4. Neural Information Processing Systems

    Conference · 2 publications · 329 citations

    2

    h-index

  5. 2022 International Conference on Robotics and Automation (ICRA)

    Conference · 2 publications · 52 citations

    2

    h-index

1–5