Model-based Reinforcement Learning

Model-Based Reinforcement Learning is a reinforcement learning paradigm that employs an learned or given environment model to simulate state transitions and rewards, thereby enabling planning and policy improvement through inferred dynamics rather than direct interaction alone.

744

Publications

49.4K

Citations

2.1K

Authors

562

Institutions

Publications per year

2017–2026

518

Authors

2.1K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    32 publications · 3.7K citations

    23

    h-index

  2. CF
    Chelsea Finn

    University of California, Berkeley, United States

    15 publications · 2.1K citations

    15

    h-index

  3. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    15 publications · 1.7K citations

    13

    h-index

  4. ML
    Michael L. Littman

    Rutgers, The State University of New Jersey, United States

    12 publications · 717 citations

    12

    h-index

  5. ND
    Nathaniel D. Daw

    Princeton University, United States

    10 publications · 4.5K citations

    10

    h-index

1–5 of 2.1K

Venues

  1. arXiv (Cornell University)

    Repository · 161 publications · 8K citations

    43

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 17 publications · 544 citations

    14

    h-index

  3. IEEE Robotics and Automation Letters

    12 publications · 411 citations

    12

    h-index

  4. Neural Information Processing Systems

    Conference · 10 publications · 675 citations

    10

    h-index

  5. 9

    h-index

1–5