Unsupervised Skill Discovery

Unsupervised Skill Discovery is a methodological framework in self-supervised robot learning that autonomously identifies and acquires reusable behavioral primitives from unlabeled environmental interactions without explicit external supervision or task-specific rewards.

16

Publications

487

Citations

50

Authors

19

Institutions

Publications per year

2017–2026

14

Authors

50

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    5 publications · 212 citations

    5

    h-index

  2. KH
    Karol Hausman

    Google (United States), United States

    4 publications · 115 citations

    4

    h-index

  3. AS
    Archit Sharma

    Stanford University, United States

    4 publications · 115 citations

    4

    h-index

  4. VK
    Vikash Kumar

    Google (United States), United States

    4 publications · 115 citations

    4

    h-index

  5. SG
    Shixiang Gu

    Google (United States), United States

    4 publications · 115 citations

    4

    h-index

1–5 of 50

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 254 citations

    7

    h-index

  2. Proceedings of the Genetic and Evolutionary Computation Conference

    Conference · 1 publications · 65 citations

    1

    h-index

  3. IEEE Robotics and Automation Letters

    1 publications · 17 citations

    1

    h-index

  4. Educational Data Mining

    Conference · 1 publications · 24 citations

    1

    h-index

  5. Artificial Intelligence

    1 publications · 52 citations

    1

    h-index

1–5