Preference-based Reward Learning

Preference-Based Reward Learning is a reward learning framework that infers a reward function by modeling preferences expressed over pairs of trajectories or behaviors, distinguishing itself from other reward learning methods through its reliance on comparative human feedback rather than absolute or numerical rewards.

19

Publications

929

Citations

66

Authors

25

Institutions

Publications per year

2017–2026

15

Variants

Pbrl

Authors

66

  1. DS
    Dorsa Sadigh

    Stanford University, United States

    4 publications · 349 citations

    4

    h-index

  2. KG
    Kun Gai

    Alibaba Group (China), China

    1 publications · 25 citations

    1

    h-index

  3. YS
    Younggyo Seo

    University of California, Berkeley, United States

    1 publications · 14 citations

    1

    h-index

  4. MJ
    Mykel J. Kochenderfer

    Stanford University, United States

    1 publications · 54 citations

    1

    h-index

  5. YD
    Yuxiao Dong

    Tsinghua University, China

    1 publications · 99 citations

    1

    h-index

1–5 of 66

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 141 citations

    4

    h-index

  2. 1

    h-index

  3. ACM Transactions on Human-Robot Interaction

    THRI · 1 publications · 12 citations

    1

    h-index

  4. Neuropsychopharmacology

    1 publications · 89 citations

    1

    h-index

  5. Journal of Abnormal & Social Psychology

    1 publications · 11 citations

    1

    h-index

1–5