Model-based Policy Optimization

Model-Based Policy Optimization is a model-based reinforcement learning framework that integrates learned dynamic models of the environment with policy optimization to improve sample efficiency and control performance by leveraging predicted transitions for planning and policy improvement.

137

Publications

6.5K

Citations

533

Authors

196

Institutions

Publications per year

2017–2026

116

Variants

Mbpo

Authors

533

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    4 publications · 426 citations

    4

    h-index

  2. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    4 publications · 360 citations

    4

    h-index

  3. HH
    Hongwen He

    Beijing Institute of Technology, China

    3 publications · 193 citations

    3

    h-index

  4. DQ
    Dawei Qiu

    Imperial College London, United Kingdom

    3 publications · 257 citations

    3

    h-index

  5. WZ
    Weinan Zhang

    Shanghai Jiao Tong University, China

    3 publications · 41 citations

    3

    h-index

1–5 of 533

Venues

  1. arXiv (Cornell University)

    Repository · 16 publications · 939 citations

    14

    h-index

  2. Applied Energy

    11 publications · 1.2K citations

    11

    h-index

  3. Energy

    5 publications · 202 citations

    5

    h-index

  4. Automation in Construction

    3 publications · 105 citations

    3

    h-index

  5. Renewable and Sustainable Energy Reviews

    3 publications · 345 citations

    3

    h-index

1–5