Inverse Model Learning

Inverse Model Learning is a method in self-supervised robot learning that predicts the actions required to achieve a desired state transition by modeling the inverse of the environment dynamics, distinguishing itself from forward models by inferring causes from effects rather than predicting effects from causes.

328

Publications

15K

Citations

975

Authors

395

Institutions

Publications per year

2017–2026

170

Authors

975

  1. JJ
    Jochen J. Steil

    Bielefeld University, Germany

    7 publications · 194 citations

    7

    h-index

  2. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    6 publications · 740 citations

    6

    h-index

  3. MK
    Mitsuo Kawato

    Advanced Telecommunications Research Institute International, Japan

    6 publications · 1.2K citations

    6

    h-index

  4. JP
    Jan Peters

    Technische Universität Darmstadt, Germany

    5 publications · 793 citations

    5

    h-index

  5. DN
    Duy Nguyen-Tuong

    Max Planck Society, Germany

    5 publications · 732 citations

    5

    h-index

1–5 of 975

Venues

  1. arXiv (Cornell University)

    Repository · 18 publications · 696 citations

    13

    h-index

  2. IEEE Robotics and Automation Letters

    7 publications · 143 citations

    7

    h-index

  3. Scientific Reports

    4 publications · 108 citations

    4

    h-index

  4. 4

    h-index

  5. 3

    h-index

1–5