Constrained Reinforcement Learning

Constrained Reinforcement Learning is a formal framework within reinforcement learning that extends the standard Markov decision process by incorporating constraints on expected cumulative costs, thereby requiring policies to optimize primary rewards while satisfying secondary performance or safety requirements.

150

Publications

6.7K

Citations

454

Authors

172

Institutions

Publications per year

2017–2026

123

Authors

454

  1. DK
    Daniel Kroening

    University of Oxford, United Kingdom

    4 publications · 112 citations

    4

    h-index

  2. MH
    Mohammadhosein Hasanbeig

    University of Oxford, United Kingdom

    4 publications · 112 citations

    4

    h-index

  3. AA
    Alessandro Abate

    University of Oxford, United Kingdom

    4 publications · 112 citations

    4

    h-index

  4. YL
    Yongshuai Liu

    Qingdao University, China

    4 publications · 178 citations

    4

    h-index

  5. YG
    Yang Guan

    Tsinghua University, China

    3 publications · 92 citations

    3

    h-index

1–5 of 454

Venues

  1. arXiv (Cornell University)

    Repository · 42 publications · 1.7K citations

    21

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 397 citations

    6

    h-index

  3. Computers & Chemical Engineering

    4 publications · 140 citations

    4

    h-index

  4. Systems & Control Letters

    3 publications · 258 citations

    3

    h-index

  5. 3

    h-index

1–5