Concepedia

Safe Policy Learning

Safe Policy Learning is a method in the field of reinforcement learning that integrates safety constraints into the policy optimization process to ensure that learned policies avoid hazardous states or actions while achieving desired performance objectives.

99

Publications

4.7K

Citations

342

Authors

121

Institutions

Publications per year

2017–2026

93

Parents

Publications

99

End-to-End Safe Reinforcement Learning through Barrier Functions for Safety-Critical Continuous Control Tasks

Richard Cheng, Gábor Orosz, Richard M. Murray et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2019 · 533 citations · Full text

, , +17

Safe reinforcement learning: A control barrier function optimization approach

Zahra Marvi, Bahare Kiumarsi · International Journal of Robust and Nonlinear Control · 2020 · 232 citations

, , +15

Recovery RL: Safe Reinforcement Learning With Learned Recovery Zones

Suraj Nair, Michael Luo, Krishnan Srinivasan et al. · IEEE Robotics and Automation Letters · 2021 · 197 citations

, , +17

Lyapunov-based Safe Policy Optimization for Continuous Control

Yinlam Chow, Ofir Nachum, Aleksandra Faust et al. · arXiv (Cornell University) · 2019 · 154 citations · Full text

, , +16

Safe deep reinforcement learning-based constrained optimal control scheme for active distribution networks

Peng Kou, Deliang Liang, Chen Wang et al. · Applied Energy · 2020 · 141 citations

, , +14

1–5 of 99

Authors

342

  1. JI
    Julian Ibarz

    Google (United States), United States

    4 publications · 303 citations

    4

    h-index

  2. CF
    Chelsea Finn

    University of California, Berkeley, United States

    3 publications · 243 citations

    3

    h-index

  3. AA
    Alessandro Abate

    University of Oxford, United Kingdom

    3 publications · 59 citations

    3

    h-index

  4. CF
    Chuchu Fan

    Massachusetts Institute of Technology, United States

    3 publications · 113 citations

    3

    h-index

  5. BE
    Benjamin Eysenbach

    Carnegie Mellon University, United States

    3 publications · 112 citations

    3

    h-index

1–5 of 342

Institutions

121

  1. Tsinghua University

    Beijing, China

    6 h-index

    21 publications

    858 citations

  2. Massachusetts Institute of Technology

    Cambridge, United States

    5 h-index

    14 publications

    446 citations

  3. University of California, Berkeley

    Berkeley, United States

    5 h-index

    21 publications

    903 citations

  4. University of Michigan

    Ann Arbor, United States

    5 h-index

    8 publications

    877 citations

  5. Stanford University

    Stanford, United States

    4 h-index

    7 publications

    496 citations

  6. Imperial College London

    London, United Kingdom

    4 h-index

    9 publications

    864 citations

  7. Google (United States)

    Mountain View, United States

    4 h-index

    4 publications

    413 citations

  8. University of Oxford

    Oxford, United Kingdom

    4 h-index

    10 publications

    298 citations

1–8 of 121

Venues

  1. arXiv (Cornell University)

    Repository · 29 publications · 971 citations

    18

    h-index

  2. Applied Energy

    3 publications · 350 citations

    3

    h-index

  3. Information Sciences

    2 publications · 36 citations

    2

    h-index

  4. Machine Learning

    2 publications · 54 citations

    2

    h-index

  5. Electric Power Systems Research

    2 publications · 93 citations

    2

    h-index

1–5