Concepedia

Policy Iteration Optimality

Policy Iteration Optimality is a theoretical construct in reinforcement learning that characterizes the condition under which a policy iteration algorithm converges to a globally optimal policy by guaranteeing that each iterative policy improvement step strictly dominates the previous policy in terms of long-term value maximization.

38

Publications

2.3K

Citations

90

Authors

65

Institutions

Publications per year

2017–2026

11

Parents

Publications

38

Adaptive optimal control for continuous-time linear systems based on policy iteration

Draguna Vrabie, Octavian Păstrăvanu, Murad Abu-Khalaf et al. · Automatica · 2008 · 925 citations

, , +12

Error bounds for approximate policy iteration

Rémi Munos · 2003 · 194 citations

, , +16

Policy Iteration Reinforcement Learning-based control using a Grey Wolf Optimizer algorithm

Iuliu Alexandru Zamfirache, Radu‐Emil Precup, Raul‐Cristian Roman et al. · Information Sciences · 2021 · 188 citations

, , +13

Policy Iteration for Decentralized Control of Markov Decision Processes

D. S. Bernstein, Christopher Amato, Eric A. Hansen et al. · Journal of Artificial Intelligence Research · 2009 · 92 citations · Full text

, , +13

Generalized Actor-Critic Learning Optimal Control in Smart Home Energy Management

Qinglai Wei, Zehua Liao, Guang Shi · IEEE Transactions on Industrial Informatics · 2020 · 68 citations

, , +16

1–5 of 38

Authors

90

  1. QW
    Qinglai Wei

    Chinese Academy of Sciences, China

    3 publications · 167 citations

    3

    h-index

  2. XC
    Xi‐Ren Cao

    Hong Kong University of Science and Technology, Hong Kong SAR China

    3 publications · 74 citations

    3

    h-index

  3. DL
    Derong Liu

    Chinese Academy of Sciences, China

    2 publications · 99 citations

    2

    h-index

  4. CB
    Christian Bender

    Technische Universität Braunschweig, Germany

    2 publications · 34 citations

    2

    h-index

  5. JS
    John Schoenmakers

    Weierstrass Institute for Applied Analysis and Stochastics, Germany

    2 publications · 34 citations

    2

    h-index

1–5 of 90

Institutions

65

  1. Hong Kong University of Science and Technology

    Hong Kong, Hong Kong

    3 h-index

    3 publications

    74 citations

  2. Vrije Universiteit Amsterdam

    Amsterdam, The Netherlands

    3 h-index

    4 publications

    111 citations

  3. Shandong Institute of Automation

    Jinan, China

    3 h-index

    8 publications

    458 citations

  4. Chinese Academy of Sciences

    Beijing, China

    3 h-index

    8 publications

    458 citations

  5. Institute of Computational Mathematics and Mathematical Geophysics

    Novosibirsk, Russia

    2 h-index

    2 publications

    34 citations

  6. Tsinghua University

    Beijing, China

    2 h-index

    3 publications

    91 citations

  7. Virginia Tech

    Blacksburg, United States

    2 h-index

    3 publications

    38 citations

  8. Technische Universität Braunschweig

    Braunschweig, Germany

    2 h-index

    2 publications

    34 citations

1–8 of 65

Venues

  1. Automatica

    4 publications · 1K citations

    3

    h-index

  2. IEEE Transactions on Parallel and Distributed Systems

    TPDS · 2 publications · 48 citations

    2

    h-index

  3. Journal of Applied Probability

    JAP · 2 publications · 57 citations

    2

    h-index

  4. 2

    h-index

  5. IEEE Transactions on Automatic Control

    2 publications · 35 citations

    2

    h-index

1–5