Concepedia

Inverse Reinforcement Learning

Inverse Reinforcement Learning is a method in reinforcement learning that infers the underlying reward function from observed agent behavior, distinguishing itself by reversing the traditional paradigm of learning policies given known rewards.

427

Publications

26.9K

Citations

1.2K

Authors

360

Institutions

Publications per year

2017–2026

307

Parents

Publications

427

Apprenticeship learning via inverse reinforcement learning

Pieter Abbeel, Andrew Y. Ng · 2004 · 2.9K citations

, , +13

Maximum Entropy Inverse Reinforcement Learning

Brian D. Ziebart, Andrew L. Maas, J. Andrew Bagnell et al. · Research Showcase @ Carnegie Mellon University (Carnegie Mellon University) · 2018 · 2.1K citations

, , +17

Socially compliant mobile robot navigation via inverse reinforcement learning

Henrik Kretzschmar, Markus Spies, Christoph Sprunk et al. · The International Journal of Robotics Research · 2016 · 471 citations

, , +17

Learning driving styles for autonomous vehicles from demonstration

Markus Kuderer, Shilpa Gulati, Wolfram Burgard · 2015 · 470 citations

, , +15

Planning for Autonomous Cars that Leverage Effects on Human Actions

Dorsa Sadigh, S. Shankar Sastry, Sanjit A. Seshia et al. · 2016 · 425 citations · Full text

, , +17

1–5 of 427

Authors

1.2K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    13 publications · 1.2K citations

    13

    h-index

  2. AD
    Anca D. Dragan

    University of California, Berkeley, United States

    12 publications · 1.6K citations

    12

    h-index

  3. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    11 publications · 4.2K citations

    11

    h-index

  4. FL
    Frank L. Lewis

    The University of Texas at Arlington, United States

    10 publications · 625 citations

    10

    h-index

  5. BL
    Bosen Lian

    The University of Texas at Arlington, United States

    10 publications · 625 citations

    10

    h-index

1–5 of 1.2K

Institutions

360

  1. University of California, Berkeley

    Berkeley, United States

    20 h-index

    99 publications

    7K citations

  2. Stanford University

    Stanford, United States

    18 h-index

    40 publications

    9.1K citations

  3. Carnegie Mellon University

    Pittsburgh, United States

    17 h-index

    42 publications

    10.8K citations

  4. The University of Texas at Austin

    Austin, United States

    11 h-index

    34 publications

    1.5K citations

  5. Tsinghua University

    Beijing, China

    10 h-index

    33 publications

    1.4K citations

  6. Georgia Institute of Technology

    Atlanta, United States

    10 h-index

    18 publications

    1.2K citations

  7. Northeastern University

    Shenyang, China

    9 h-index

    18 publications

    1.3K citations

  8. Massachusetts Institute of Technology

    Cambridge, United States

    9 h-index

    22 publications

    1.2K citations

1–8 of 360

Venues

  1. arXiv (Cornell University)

    Repository · 77 publications · 3.9K citations

    31

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 13 publications · 309 citations

    12

    h-index

  3. IEEE Robotics and Automation Letters

    11 publications · 599 citations

    11

    h-index

  4. 8

    h-index

  5. Information Sciences

    5 publications · 95 citations

    5

    h-index

1–5