Preference-based Learning

Preference-Based Learning is a machine learning paradigm that belongs to the class of learning from human feedback, differing from other paradigms by specifically utilizing pairwise or ranked preferences to infer a reward function or policy that aligns with human judgments.

216

Publications

10.7K

Citations

569

Authors

302

Institutions

Publications per year

2017–2026

88

Authors

569

  1. EH
    Eyke Hüllermeier

    Philipps University of Marburg, Germany

    11 publications · 930 citations

    11

    h-index

  2. GN
    Georgios N. Yannakakis

    IT University of Copenhagen, Denmark

    9 publications · 535 citations

    9

    h-index

  3. DS
    Dorsa Sadigh

    Stanford University, United States

    8 publications · 449 citations

    8

    h-index

  4. JF
    Johannes Fürnkranz

    Technische Universität Darmstadt, Germany

    6 publications · 884 citations

    6

    h-index

  5. WC
    Weiwei Cheng

    Nanjing University of Finance and Economics, China

    4 publications · 702 citations

    4

    h-index

1–5 of 569

Venues

  1. arXiv (Cornell University)

    Repository · 17 publications · 316 citations

    12

    h-index

  2. Machine Learning

    5 publications · 258 citations

    5

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 154 citations

    4

    h-index

  4. Journal of Applied Behavior Analysis

    JABA · 4 publications · 207 citations

    4

    h-index

  5. Artificial Intelligence

    3 publications · 609 citations

    3

    h-index

1–5