Concepedia

Reward Normalization

Reward Normalization is a method in reward design that scales and adjusts reward signals to a consistent range or statistical distribution, enabling stable and efficient learning in reinforcement learning systems by mitigating the impact of reward magnitude variability.

10

Publications

477

Citations

28

Authors

25

Institutions

Publications per year

2017–2026

7

Parents

Publications

10

Learning values across many orders of magnitude

Hado van Hasselt, Arthur Guez, Matteo Hessel et al. · arXiv (Cornell University) · 2016 · 87 citations · Full text

, , +16

Free choice shapes normalized value signals in medial orbitofrontal cortex

Hiroshi Yamada, Kenway Louie, Agnieszka Tymula et al. · Nature Communications · 2018 · 86 citations · Full text

, , +16

Multiple timescales of normalized value coding underlie adaptive choice behavior

Jan Zimmermann, Paul W. Glimcher, Kenway Louie · Nature Communications · 2018 · 72 citations · Full text

, , +16

Who will pay for the “bicycle cemetery”? Evolutionary game analysis of recycling abandoned shared bicycles under dynamic reward and punishment

Qingqing Sun, Hong Chen, Ruyin Long et al. · European Journal of Operational Research · 2022 · 67 citations

, , +16

It’s all relative: Reward-induced cognitive control modulation depends on context.

A. Ross Otto, Eliana Vassena · Journal of Experimental Psychology General · 2020 · 58 citations

, , +17

1–5 of 10

Authors

28

  1. KL
    Kenway Louie

    New York University, United States

    3 publications · 179 citations

    3

    h-index

  2. HV
    Hado van Hasselt

    Google DeepMind (United Kingdom), United Kingdom

    2 publications · 98 citations

    2

    h-index

  3. AG
    Arthur Guez

    Google DeepMind (United Kingdom), United Kingdom

    2 publications · 98 citations

    2

    h-index

  4. PW
    Paul W. Glimcher

    New York University, United States

    2 publications · 158 citations

    2

    h-index

  5. DS
    David Silver

    Google DeepMind (United Kingdom), United Kingdom

    2 publications · 98 citations

    2

    h-index

1–5 of 28

Institutions

25

  1. New York University

    New York, United States

    3 h-index

    8 publications

    581 citations

  2. UNSW Sydney

    Sydney, Australia

    1 h-index

    1 publications

    86 citations

  3. Huazhong University of Science and Technology

    Wuhan, China

    1 h-index

    4 publications

    88 citations

  4. École Normale Supérieure

    Bujumbura, Burundi

    1 h-index

    2 publications

    64 citations

  5. Jiangnan University

    Wuxi, China

    1 h-index

    2 publications

    134 citations

  6. East China University of Science and Technology

    Shanghai, China

    1 h-index

    1 publications

    22 citations

  7. Northwestern University

    Evanston, United States

    1 h-index

    5 publications

    105 citations

  8. University of Washington

    Seattle, United States

    1 h-index

    1 publications

    21 citations

1–8 of 25

Venues

  1. Nature Communications

    2 publications · 158 citations

    2

    h-index

  2. arXiv (Cornell University)

    Repository · 2 publications · 98 citations

    2

    h-index

  3. European Journal of Operational Research

    1 publications · 67 citations

    1

    h-index

  4. PLoS Computational Biology

    1 publications · 21 citations

    1

    h-index

  5. eLife

    1 publications · 32 citations

    1

    h-index

1–5