Concepedia

Policy Iteration

Policy Iteration is a dynamic programming algorithm in the context of Markov Decision Processes that iteratively improves a policy by alternating between policy evaluation, which computes the value function for the current policy, and policy improvement, which updates the policy using the greedy action-selection rule with respect to the computed value function.

2.2K

Publications

248.2K

Citations

4.4K

Authors

1.2K

Institutions

Publications per year

2017–2026

972

Parents

Children

Publications

2.2K

Reinforcement Learning: An Introduction

Richard S. Sutton, Andy Barto · IEEE Transactions on Neural Networks · 1998 · 27.1K citations

, , +12

Reinforcement Learning: An Introduction

IEEE Transactions on Neural Networks · 2005 · 25.8K citations

, , +12

Diagnosing Non-Intermittent Anomalies in Reinforcement Learning Policy Executions (Short Paper)

arXiv (Cornell University) · 2017 · 11.3K citations · Full text

, , +16

Reinforcement Learning: A Survey

Leslie Pack Kaelbling, Michael L. Littman, Andrew Moore · Journal of Artificial Intelligence Research · 1996 · 8.8K citations · Full text

, , +15

Reinforcement Learning: An Introduction

Jeffrey D. Johnson, Jinghong Li, Zengshi Chen · Neurocomputing · 2000 · 8.7K citations

, , +12

1–5 of 2.2K

Authors

4.4K

  1. FL
    Frank L. Lewis

    The University of Texas at Arlington, United States

    46 publications · 5.9K citations

    31

    h-index

  2. RM
    Rémi Munos

    Google (United States), United States

    25 publications · 2.2K citations

    24

    h-index

  3. DL
    Derong Liu

    Chinese Academy of Sciences, China

    27 publications · 4.1K citations

    24

    h-index

  4. SL
    Sergey Levine

    University of California, Berkeley, United States

    24 publications · 7.2K citations

    19

    h-index

  5. RS
    Richard S. Sutton

    University of Alberta, Canada

    23 publications · 36.6K citations

    18

    h-index

1–5 of 4.4K

Institutions

1.2K

  1. Chinese Academy of Sciences

    Beijing, China

    36 h-index

    106 publications

    10.7K citations

  2. Shandong Institute of Automation

    Jinan, China

    33 h-index

    90 publications

    9.2K citations

  3. Massachusetts Institute of Technology

    Cambridge, United States

    32 h-index

    97 publications

    11.7K citations

  4. Carnegie Mellon University

    Pittsburgh, United States

    31 h-index

    69 publications

    21.6K citations

  5. University of Massachusetts Amherst

    Amherst Center, United States

    28 h-index

    70 publications

    12K citations

  6. Northeastern University

    Shenyang, China

    26 h-index

    77 publications

    8.6K citations

  7. University of California, Berkeley

    Berkeley, United States

    26 h-index

    84 publications

    30.8K citations

  8. Stanford University

    Stanford, United States

    25 h-index

    62 publications

    11.5K citations

1–8 of 1.2K

Venues

  1. arXiv (Cornell University)

    Repository · 268 publications · 28.9K citations

    54

    h-index

  2. 35

    h-index

  3. IEEE Transactions on Automatic Control

    36 publications · 2.7K citations

    27

    h-index

  4. Machine Learning

    35 publications · 11.8K citations

    24

    h-index

  5. IEEE Transactions on Cybernetics

    31 publications · 2.4K citations

    24

    h-index

1–5