Sparse Demonstration Learning

Sparse Demonstration Learning is a learning paradigm within the broader domain of Learning from Demonstration that specifically addresses the challenge of acquiring effective policies from a limited and non-continuous set of demonstration instances, thereby distinguishing itself by its focus on data efficiency and generalization under sparse supervisory signals.

4

Publications

87

Citations

19

Authors

9

Institutions

Publications per year

2017–2026

4

Authors

19

  1. NE
    Neta Ezer

    Northrop Grumman (United States), United States

    1 publications · 33 citations

    1

    h-index

  2. WJ
    Wanxin Jin

    Purdue University West Lafayette, United States

    1 publications · 33 citations

    1

    h-index

  3. PP
    Panupong Pasupat

    Stanford University, United States

    1 publications · 16 citations

    1

    h-index

  4. AS
    Akshay Sarvesh

    1 publications · 27 citations

    1

    h-index

  5. PL
    Percy Liang

    Stanford University, United States

    1 publications · 16 citations

    1

    h-index

1–5 of 19

Venues

  1. arXiv (Cornell University)

    Repository · 3 publications · 54 citations

    3

    h-index

  2. IEEE Transactions on Robotics

    1 publications · 33 citations

    1

    h-index

1–2