Concepedia

Learned World Models

Learned World Models is a computational framework in model-based robot learning that autonomously acquires, through sensorimotor interaction with the environment, an internal dynamic representation of the external world’s causal structure, distinguished from other system identification approaches by its reliance on learned, data-driven approximations of transition and observation dynamics rather than hand-engineered physical models.

124

Publications

7.3K

Citations

354

Authors

132

Institutions

Publications per year

2017–2026

57

Parents

Publications

124

Dyna, an integrated architecture for learning, planning, and reacting

Richard S. Sutton · ACM SIGART Bulletin · 1991 · 767 citations

, , +15

Learning-induced autonomy of sensorimotor systems

Danielle S. Bassett, Muzhi Yang, Nicholas F. Wymbs et al. · Nature Neuroscience · 2015 · 660 citations · Full text

, , +13

End-to-End Autonomous Driving: Challenges and Frontiers

Li Chen, Penghao Wu, Kashyap Chitta et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024 · 445 citations

, , +17

Recurrent World Models Facilitate Policy Evolution

David Ha, Jürgen Schmidhuber · arXiv (Cornell University) · 2018 · 410 citations · Full text

, , +12

Learning compact 3D models of indoor and outdoor environments with a mobile robot

Dirk Hähnel, Wolfram Burgard, Sebastian Thrun · Robotics and Autonomous Systems · 2003 · 316 citations

, , +15

1–5 of 124

Authors

354

  1. DH
    Danijar Hafner

    Google (United States), United States

    6 publications · 394 citations

    6

    h-index

  2. JB
    Jimmy Ba

    University of Toronto, Canada

    4 publications · 334 citations

    4

    h-index

  3. JS
    Jürgen Schmidhuber

    Dalle Molle Institute for Artificial Intelligence Research, Switzerland

    4 publications · 793 citations

    4

    h-index

  4. ST
    Sebastian Thrun

    Carnegie Mellon University, United States

    4 publications · 476 citations

    4

    h-index

  5. TL
    Timothy Lillicrap

    Google (United States), United States

    4 publications · 334 citations

    4

    h-index

1–5 of 354

Institutions

132

  1. Massachusetts Institute of Technology

    Cambridge, United States

    10 h-index

    20 publications

    1.5K citations

  2. Google (United States)

    Mountain View, United States

    9 h-index

    19 publications

    2.3K citations

  3. The University of Texas at Austin

    Austin, United States

    5 h-index

    12 publications

    650 citations

  4. University of Toronto

    Toronto, Canada

    4 h-index

    5 publications

    411 citations

  5. University of California, Berkeley

    Berkeley, United States

    4 h-index

    8 publications

    315 citations

  6. University of Oxford

    Oxford, United Kingdom

    4 h-index

    4 publications

    88 citations

  7. Technical University of Munich

    Munich, Germany

    3 h-index

    12 publications

    238 citations

  8. California Institute of Technology

    Pasadena, United States

    3 h-index

    4 publications

    77 citations

1–8 of 132

Venues

  1. arXiv (Cornell University)

    Repository · 32 publications · 1.9K citations

    18

    h-index

  2. Robotics and Autonomous Systems

    4 publications · 367 citations

    4

    h-index

  3. Autonomous Robots

    3 publications · 66 citations

    3

    h-index

  4. KI - Künstliche Intelligenz

    2 publications · 23 citations

    2

    h-index

  5. Machine Learning

    2 publications · 122 citations

    2

    h-index

1–5