Task Reward Specification

Task Reward Specification is a formal academic construct within the domain of Reward Design that defines the precise criteria, structure, and allocation mechanism through which rewards are assigned to agents in response to specific tasks, distinguishing it from broader reward modeling approaches by its focus on task-specific incentive alignment.

16

Publications

632

Citations

66

Authors

19

Institutions

Publications per year

2017–2026

11

Authors

66

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    3 publications · 60 citations

    3

    h-index

  2. AG
    Anchit Gupta

    Stanford University, United States

    2 publications · 124 citations

    2

    h-index

  3. JB
    Jonathan Booher

    Stanford University, United States

    2 publications · 124 citations

    2

    h-index

  4. CF
    Chelsea Finn

    University of California, Berkeley, United States

    2 publications · 29 citations

    2

    h-index

  5. DG
    Daniel Geng

    University of California, Berkeley, United States

    2 publications · 29 citations

    2

    h-index

1–5 of 66

Venues

  1. arXiv (Cornell University)

    Repository · 7 publications · 266 citations

    7

    h-index

  2. International Conference on Machine Learning

    Conference · 1 publications · 129 citations

    1

    h-index

  3. Autonomous Agents and Multi-Agent Systems

    1 publications · 22 citations

    1

    h-index

  4. Cognitive Psychology

    1 publications · 12 citations

    1

    h-index

  5. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 19 citations

    1

    h-index

1–5