Self-supervised Reinforcement Learning

Self-Supervised Reinforcement Learning is a reinforcement learning paradigm that falls under the broader category of self-supervised learning methods, distinguished by its use of autonomously generated supervision signals from the agent's environment interactions to guide representation learning and policy optimization without reliance on externally annotated data.

74

Publications

4.6K

Citations

260

Authors

78

Institutions

Publications per year

2017–2026

70

Authors

260

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    7 publications · 1.2K citations

    7

    h-index

  2. SB
    Shikhar Bahl

    Carnegie Mellon University, United States

    4 publications · 443 citations

    4

    h-index

  3. AN
    Ashvin Nair

    University of California, Berkeley, United States

    4 publications · 443 citations

    4

    h-index

  4. VH
    Vitchyr H. Pong

    University of California, Berkeley, United States

    4 publications · 443 citations

    4

    h-index

  5. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    4 publications · 154 citations

    4

    h-index

1–5 of 260

Venues

  1. arXiv (Cornell University)

    Repository · 29 publications · 2.2K citations

    19

    h-index

  2. IEEE Robotics and Automation Letters

    4 publications · 76 citations

    4

    h-index

  3. Neurocomputing

    1 publications · 19 citations

    2

    h-index

  4. 1

    h-index

  5. Journal of Power Sources

    1 publications · 47 citations

    1

    h-index

1–5