Policy Optimization

Policy Optimization is a reinforcement learning method that specifies the systematic approach to improving a policy by directly adjusting its parameters to maximize cumulative rewards, distinguishing it from value-based or model-based strategies through its focus on explicit policy representation and gradient-driven or iterative refinement.

945

Publications

62.7K

Citations

3.1K

Authors

804

Institutions

Publications per year

2017–2026

778

Authors

3.1K

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    12 publications · 4.3K citations

    12

    h-index

  2. JP
    Jan Peters

    Technische Universität Darmstadt, Germany

    10 publications · 374 citations

    10

    h-index

  3. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    9 publications · 3.5K citations

    9

    h-index

  4. JP
    Jian Peng

    University of Illinois Urbana-Champaign, United States

    9 publications · 258 citations

    9

    h-index

  5. NH
    Nicolas Heess

    Google (United States), United States

    8 publications · 734 citations

    8

    h-index

1–5 of 3.1K

Venues

  1. arXiv (Cornell University)

    Repository · 174 publications · 24K citations

    45

    h-index

  2. IEEE Access

    25 publications · 963 citations

    20

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 16 publications · 688 citations

    14

    h-index

  4. Applied Sciences

    13 publications · 287 citations

    13

    h-index

  5. Sensors

    10 publications · 365 citations

    10

    h-index

1–5