Reward Constrained Learning

Reward Constrained Learning is a constrained optimization framework in reinforcement learning where policy learning is governed by explicit bounds on expected cumulative reward, distinguishing it from general safety-aware methods by enforcing hard constraints on reward attainment rather than penalizing unsafe behaviors.

37

Publications

2K

Citations

124

Authors

46

Institutions

Publications per year

2017–2026

33

Authors

124

  1. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    3 publications · 289 citations

    3

    h-index

  2. DB
    Djallel Bouneffouf

    IBM (United States), United States

    2 publications · 70 citations

    2

    h-index

  3. TP
    Tu-Hoa Pham

    IBM Research - Tokyo, Japan

    2 publications · 129 citations

    2

    h-index

  4. CT
    Chen Tessler

    Technion – Israel Institute of Technology, Israel

    2 publications · 277 citations

    2

    h-index

  5. HD
    Hal Daumé

    University of Maryland, College Park, United States

    2 publications · 59 citations

    2

    h-index

1–5 of 124

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 528 citations

    11

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 4 publications · 250 citations

    4

    h-index

  3. Neural Networks

    1 publications · 21 citations

    1

    h-index

  4. Control Engineering Practice

    1 publications · 14 citations

    1

    h-index

  5. Sensors

    1 publications · 16 citations

    1

    h-index

1–5