Concepedia

Safe Model-based Reinforcement Learning

Safe Model-Based Reinforcement Learning is a model-based reinforcement learning framework that incorporates explicit safety constraints and risk-aware planning mechanisms to ensure reliable and provably safe policy synthesis within uncertain or high-stakes environments.

26

Publications

2K

Citations

102

Authors

45

Institutions

Publications per year

2017–2026

25

Parents

Publications

26

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 Model-based Reinforcement Learning with Stability Guarantees

Felix Berkenkamp, Matteo Turchetta, Angela P. Schoellig et al. · arXiv (Cornell University) · 2017 · 337 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

Safe reinforcement learning for real-time automatic control in a smart energy-hub

Dawei Qiu, Zihang Dong, Xi Zhang et al. · Applied Energy · 2022 · 121 citations

, , +16

Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks

Brijen Thananjeyan, Ashwin Balakrishna, Ugo Rosolia et al. · IEEE Robotics and Automation Letters · 2020 · 90 citations

, , +17

1–5 of 26

Authors

102

  1. JW
    Joel W. Burdick

    California Institute of Technology, United States

    2 publications · 576 citations

    2

    h-index

  2. RM
    Richard M. Murray

    California Institute of Technology, United States

    2 publications · 576 citations

    2

    h-index

  3. GO
    Gábor Orosz

    University of Michigan, United States

    2 publications · 576 citations

    2

    h-index

  4. GŠ
    Goran Štrbac

    Imperial College London, United Kingdom

    2 publications · 209 citations

    2

    h-index

  5. DQ
    Dawei Qiu

    Imperial College London, United Kingdom

    2 publications · 209 citations

    2

    h-index

1–5 of 102

Institutions

45

  1. California Institute of Technology

    Pasadena, United States

    3 h-index

    7 publications

    1.8K citations

  2. Imperial College London

    London, United Kingdom

    2 h-index

    7 publications

    748 citations

  3. Tsinghua University

    Beijing, China

    2 h-index

    8 publications

    264 citations

  4. University of Michigan

    Ann Arbor, United States

    2 h-index

    2 publications

    576 citations

  5. Tianjin University

    Tianjin, China

    2 h-index

    7 publications

    342 citations

  6. Tsinghua–Berkeley Shenzhen Institute

    Shenzhen, China

    2 h-index

    5 publications

    166 citations

  7. Boston University

    Boston, United States

    1 h-index

    2 publications

    22 citations

  8. University of Illinois Chicago

    Chicago, United States

    1 h-index

    1 publications

    71 citations

1–8 of 45

Venues

  1. Applied Energy

    4 publications · 432 citations

    4

    h-index

  2. arXiv (Cornell University)

    Repository · 3 publications · 397 citations

    3

    h-index

  3. IEEE Robotics and Automation Letters

    2 publications · 108 citations

    2

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 533 citations

    1

    h-index

  5. Ocean & Coastal Management

    1 publications · 48 citations

    1

    h-index

1–5