Action Schema Learning

Action Schema Learning is a computational framework within the domain of cognitive robotics and artificial intelligence that enables an agent to acquire, refine, and generalize hierarchical action representations by inferring structured rules—comprising preconditions, effects, and procedural constraints—from sequences of observed or experienced interactions with an environment.

30

Publications

1.6K

Citations

72

Authors

41

Institutions

Publications per year

2017–2026

8

Authors

72

  1. FT
    Felipe Trevizan

    Australian National University, Australia

    3 publications · 95 citations

    3

    h-index

  2. LX
    Lexing Xie

    Australian National University, Australia

    3 publications · 95 citations

    3

    h-index

  3. ST
    Sylvie Thiébaux

    Australian National University, Australia

    3 publications · 95 citations

    3

    h-index

  4. ST
    Sam Toyer

    Australian National University, Australia

    3 publications · 95 citations

    3

    h-index

  5. MA
    Michael A. Arbib

    University of Southern California, United States

    2 publications · 57 citations

    2

    h-index

1–5 of 72

Venues

  1. arXiv (Cornell University)

    Repository · 2 publications · 41 citations

    2

    h-index

  2. Rutgers University Community Repository (Rutgers University)

    Repository · 1 publications · 20 citations

    1

    h-index

  3. Journal of Experimental Psychology Applied

    1 publications · 47 citations

    1

    h-index

  4. Adaptive Behavior

    1 publications · 42 citations

    1

    h-index

  5. 1

    h-index

1–5