Domain Randomization

Domain Randomization is a simulation-based training methodology that systematically varies environmental parameters across a broad distribution during locomotion learning to enhance sim-to-real transfer by increasing policy robustness to domain shifts.

171

Publications

11.6K

Citations

589

Authors

181

Institutions

Publications per year

2017–2026

170

Authors

589

  1. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    14 publications · 3.7K citations

    13

    h-index

  2. LP
    Lerrel Pinto

    Carnegie Mellon University, United States

    6 publications · 398 citations

    6

    h-index

  3. WZ
    Wojciech Zaremba

    New York University, United States

    5 publications · 3.7K citations

    5

    h-index

  4. SL
    Sergey Levine

    University of California, Berkeley, United States

    4 publications · 259 citations

    4

    h-index

  5. PW
    Peter Welinder

    California Institute of Technology, United States

    4 publications · 772 citations

    4

    h-index

1–5 of 589

Venues

  1. arXiv (Cornell University)

    Repository · 36 publications · 1.9K citations

    21

    h-index

  2. IEEE Robotics and Automation Letters

    7 publications · 281 citations

    9

    h-index

  3. 5

    h-index

  4. 2

    h-index

  5. IEEE Transactions on Robotics

    2 publications · 338 citations

    2

    h-index

1–5