Reward Models

Reward Models is a computational framework within reinforcement learning that formalizes the specification of desired agent behavior by defining the scalar feedback signal, distinguishing it from alternative decision-making mechanisms through its focus on learning or modeling the reward function from human preferences or environmental interactions.

232

Publications

15.7K

Citations

640

Authors

263

Institutions

Publications per year

2017–2026

63

Authors

640

  1. KS
    Kishor S. Trivedi

    Duke University, United States

    11 publications · 724 citations

    11

    h-index

  2. JK
    Joost-Pieter Katoen

    RWTH Aachen University, Germany

    6 publications · 473 citations

    6

    h-index

  3. BR
    Boudewijn R. Haverkort

    University of Twente, Netherlands

    5 publications · 217 citations

    5

    h-index

  4. MT
    Miklós Telek

    Budapest Institute, Hungary

    4 publications · 80 citations

    4

    h-index

  5. LC
    Lucia Cloth

    University of Twente, Netherlands

    4 publications · 177 citations

    4

    h-index

1–5 of 640

Venues

  1. arXiv (Cornell University)

    Repository · 15 publications · 1.1K citations

    13

    h-index

  2. Performance Evaluation

    6 publications · 509 citations

    6

    h-index

  3. IEEE Transactions on Reliability

    5 publications · 205 citations

    5

    h-index

  4. Operations Research

    4 publications · 373 citations

    4

    h-index

  5. IEEE Transactions on Computers

    3 publications · 174 citations

    3

    h-index

1–5