Concepedia

Average Reward Q-learning

Average Reward Q-Learning is a reinforcement learning algorithm that extends the standard Q-Learning framework by optimizing the expected average reward per time step rather than the discounted cumulative reward, thereby focusing on long-term steady-state performance in ergodic Markov decision processes.

43

Publications

1.6K

Citations

118

Authors

62

Institutions

Publications per year

2017–2026

21

Parents

Publications

43

Path planning for intelligent robots based on deep Q-learning with experience replay and heuristic knowledge

Lan Jiang, Hongyun Huang, Zuohua Ding · IEEE/CAA Journal of Automatica Sinica · 2019 · 154 citations

, , +14

Fitted Q-iteration in continuous action-space MDPs

András Antos, Csaba Szepesvári, Rémi Munos · HAL (Le Centre pour la Communication Scientifique Directe) · 2007 · 149 citations · Full text

, , +15

Q-Learning: Flexible Learning About Useful Utilities

Erica E. M. Moodie, Nema Dean, Yue Sun · Statistics in Biosciences · 2013 · 110 citations

, , +7

A Reinforcement Learning Algorithm Based on Policy Iteration for Average Reward: Empirical Results with Yield Management and Convergence Analysis

Abhijit Gosavi · Machine Learning · 2004 · 96 citations · Full text

, , +16

Lenient Multi-Agent Deep Reinforcement Learning

Gregory Palmer, Karl Tuyls, Daan Bloembergen et al. · 2018 · 83 citations · Full text

, , +11

1–5 of 43

Authors

118

  1. SB
    Shalabh Bhatnagar

    Indian Institute of Science Bangalore, India

    2 publications · 101 citations

    3

    h-index

  2. HS
    Hiteshi Sharma

    University of Southern California, United States

    2 publications · 49 citations

    2

    h-index

  3. HL
    Haipeng Luo

    University of Southern California, United States

    2 publications · 49 citations

    2

    h-index

  4. RM
    Rémi Munos

    Google (United States), United States

    2 publications · 168 citations

    2

    h-index

  5. CW
    Chen-Yu Wei

    University of Southern California, United States

    2 publications · 49 citations

    2

    h-index

1–5 of 118

Institutions

62

  1. Institut national de recherche en sciences et technologies du numérique

    Le Chesnay-Rocquencourt, France

    4 h-index

    4 publications

    245 citations

  2. Indian Institute of Science Bangalore

    Bengaluru, India

    3 h-index

    4 publications

    202 citations

  3. California Southern University

    Chandler, United States

    2 h-index

    5 publications

    139 citations

  4. University of Alberta

    Edmonton, Canada

    2 h-index

    4 publications

    242 citations

  5. University of Southern California

    Los Angeles, United States

    2 h-index

    5 publications

    139 citations

  6. National Electronics and Computer Technology Center

    Pathum Thani, Thailand

    1 h-index

    1 publications

    19 citations

  7. AT&T (United States)

    Bedminster, United States

    1 h-index

    1 publications

    18 citations

  8. University at Buffalo, State University of New York

    Buffalo, United States

    1 h-index

    1 publications

    96 citations

1–8 of 62

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 63 citations

    4

    h-index

  2. International Conference on Machine Learning

    Conference · 2 publications · 50 citations

    2

    h-index

  3. 1

    h-index

  4. Systems & Control Letters

    1 publications · 22 citations

    1

    h-index

  5. Machine Learning

    1 publications · 96 citations

    1

    h-index

1–5