Proximal Policy Optimization

Proximal Policy Optimization is a policy gradient reinforcement learning algorithm that belongs to the class of trust-region optimization methods, distinguished by its use of clipped probability ratios to stabilize training through limited step sizes without requiring manual tuning of learning rates.

501

Publications

32.9K

Citations

1.9K

Authors

560

Institutions

Publications per year

2017–2026

501

Authors

1.9K

  1. ZH
    Zhu Han

    University of Houston, United States

    7 publications · 334 citations

    7

    h-index

  2. ZY
    Zhuoran Yang

    Princeton University, United States

    6 publications · 268 citations

    6

    h-index

  3. CS
    Choong Seon Hong

    Kyung Hee University, South Korea

    6 publications · 247 citations

    6

    h-index

  4. PW
    Peng Wei

    Iowa State University, United States

    6 publications · 203 citations

    6

    h-index

  5. ZW
    Zhaoran Wang

    Princeton University, United States

    5 publications · 207 citations

    5

    h-index

1–5 of 1.9K

Venues

  1. arXiv (Cornell University)

    Repository · 52 publications · 13.4K citations

    26

    h-index

  2. IEEE Access

    29 publications · 1.1K citations

    21

    h-index

  3. IEEE Internet of Things Journal

    17 publications · 1.2K citations

    16

    h-index

  4. Sensors

    17 publications · 566 citations

    15

    h-index

  5. IEEE Transactions on Vehicular Technology

    13 publications · 910 citations

    12

    h-index

1–5