Policy Convergence Analysis

Policy Convergence Analysis is a formal method in reinforcement learning that systematically evaluates the conditions and rate under which iterative policy improvement processes converge to an optimal or stationary policy within the framework of dynamic programming.

377

Publications

33.2K

Citations

697

Authors

335

Institutions

Publications per year

2017–2026

117

Authors

697

  1. YL
    Yingbin Liang

    The Ohio State University, United States

    8 publications · 192 citations

    8

    h-index

  2. ZY
    Zhuoran Yang

    Princeton University, United States

    7 publications · 523 citations

    7

    h-index

  3. CK
    Christoph Knill

    Ludwig-Maximilians-Universität München, Germany

    7 publications · 1.9K citations

    7

    h-index

  4. TX
    Tengyu Xu

    The Ohio State University, United States

    7 publications · 176 citations

    7

    h-index

  5. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    6 publications · 201 citations

    6

    h-index

1–5 of 697

Venues

  1. arXiv (Cornell University)

    Repository · 40 publications · 1.5K citations

    22

    h-index

  2. Journal of European Public Policy

    JEPP · 13 publications · 2.1K citations

    13

    h-index

  3. Mathematics of Operations Research

    8 publications · 485 citations

    8

    h-index

  4. SIAM Journal on Control and Optimization

    7 publications · 359 citations

    7

    h-index

  5. Automatica

    8 publications · 503 citations

    7

    h-index

1–5