Concepedia

Classical Policy Iteration

Classical Policy Iteration is a dynamic programming algorithm in reinforcement learning that iteratively alternates between policy evaluation and policy improvement steps to converge to an optimal policy for a Markov decision process.

12

Publications

1.1K

Citations

29

Authors

17

Institutions

Publications per year

2017–2026

3

Parents

Publications

12

Approximate policy iteration: a survey and some new methods

Dimitri P. Bertsekas · Journal of Control Theory and Applications · 2011 · 278 citations · Full text

, , +12

Reinforcement learning and optimal adaptive control: An overview and implementation examples

Said Ghani Khan, Guido Herrmann, Frank L. Lewis et al. · Annual Reviews in Control · 2012 · 232 citations

, , +16

Soar-RL: integrating reinforcement learning with Soar

Shelley Nason, John E. Laird · Cognitive Systems Research · 2004 · 139 citations

, , +11

An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value Function

Hajime Kimura, Shigenobu Kobayashi · Tokyo Tech Research Repository (Tokyo Institute of Technology) · 1998 · 109 citations

, , +11

A synthesis of automated planning and reinforcement learning for efficient, robust decision-making

Matteo Leonetti, Luca Iocchi, Peter Stone · Artificial Intelligence · 2016 · 102 citations · Full text

, , +14

1–5 of 12

Authors

29

  1. SK
    Shigenobu Kobayashi

    Tokyo Institute of Technology, Japan

    2 publications · 158 citations

    2

    h-index

  2. HK
    Hajime Kimura

    Osaka Research Institute of Industrial Science and Technology, Japan

    2 publications · 158 citations

    2

    h-index

  3. UY
    Uri Yechiali

    Tel Aviv University, Israel

    1 publications · 10 citations

    1

    h-index

  4. FG
    Fredrik Gustafsson

    Linköping University, Sweden

    1 publications · 59 citations

    1

    h-index

  5. ML
    Matteo Leonetti

    University of Leeds, United Kingdom

    1 publications · 102 citations

    1

    h-index

1–5 of 29

Institutions

17

  1. University of Southern California

    Los Angeles, United States

    2 h-index

    3 publications

    91 citations

  2. Tel Aviv University

    Tel Aviv, Israel

    1 h-index

    1 publications

    10 citations

  3. University of Leeds

    Leeds, United Kingdom

    1 h-index

    1 publications

    102 citations

  4. Indian Institute of Technology Delhi

    New Delhi, India

    1 h-index

    1 publications

    16 citations

  5. Sapienza University of Rome

    Rome, Italy

    1 h-index

    1 publications

    102 citations

  6. University of California, Berkeley

    Berkeley, United States

    1 h-index

    1 publications

    59 citations

  7. Massachusetts Institute of Technology

    Cambridge, United States

    1 h-index

    1 publications

    278 citations

  8. Robotics Research (United States)

    Cincinnati, United States

    1 h-index

    1 publications

    232 citations

1–8 of 17

Venues

  1. 1

    h-index

  2. Annual Reviews in Control

    1 publications · 232 citations

    1

    h-index

  3. Artificial Intelligence

    1 publications · 102 citations

    1

    h-index

  4. IEEE Transactions on Automatic Control

    1 publications · 59 citations

    1

    h-index

  5. IEEE Transactions on Communications

    1 publications · 16 citations

    1

    h-index

1–5