Concepedia

Neural Value Approximation

Neural Value Approximation is a value function approximation method in reinforcement learning that uses neural networks as the function approximator to estimate the value of states or state-action pairs, distinguishing itself from linear or table-based approximators by leveraging nonlinear representations for scalability and generalization in large or continuous state spaces.

5

Publications

694

Citations

20

Authors

9

Institutions

Publications per year

2017–2026

4

Parents

Publications

5

A distributional code for value in dopamine-based reinforcement learning

Will Dabney, Zeb Kurth‐Nelson, Naoshige Uchida et al. · Nature · 2020 · 476 citations · Full text

, , +13

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

Bohan Zhuang, Chunhua Shen, Mingkui Tan et al. · 2019 · 168 citations

, , +16

Bridging Exploration and General Function Approximation in Reinforcement Learning: Provably Efficient Kernel and Neural Value Iterations.

Zhuoran Yang, Chi Jin, Zhaoran Wang et al. · arXiv (Cornell University) · 2020 · 18 citations · Full text

, , +16

A reinforcement learning algorithm for neural networks with incremental learning ability

N. Shiraga, Seiichi Ozawa, Shigeo Abe · 2002 · 16 citations

, , +11

Structured Binary Neural Networks for Accurate Image Classification and Semantic Segmentation

Bohan Zhuang, Chunhua Shen, Mingkui Tan et al. · arXiv (Cornell University) · 2018 · 16 citations · Full text

, , +16

1–5 of 5

Authors

20

  1. IR
    Ian Reid

    The University of Adelaide, Australia

    2 publications · 184 citations

    2

    h-index

  2. BZ
    Bohan Zhuang

    Monash University, Australia

    2 publications · 184 citations

    2

    h-index

  3. LL
    Lingqiao Liu

    The University of Adelaide, Australia

    2 publications · 184 citations

    2

    h-index

  4. CS
    Chunhua Shen

    The University of Adelaide, Australia

    2 publications · 184 citations

    2

    h-index

  5. MT
    Mingkui Tan

    South China University of Technology, China

    2 publications · 184 citations

    2

    h-index

1–5 of 20

Institutions

9

  1. Google DeepMind (United Kingdom)

    London, United Kingdom

    1 h-index

    5 publications

    2.4K citations

  2. Oxford Centre for Computational Neuroscience

    Oxford, United Kingdom

    1 h-index

    1 publications

    476 citations

  3. Prostate Cancer Research

    London, United Kingdom

    1 h-index

    1 publications

    476 citations

  4. South China University of Technology

    Guangzhou, China

    1 h-index

    2 publications

    336 citations

  5. Kobe University

    Kobe, Japan

    1 h-index

    3 publications

    48 citations

  6. The University of Adelaide

    Adelaide, Australia

    1 h-index

    5 publications

    840 citations

  7. Harvard University

    Cambridge, United States

    1 h-index

    2 publications

    952 citations

  8. University College London

    London, United Kingdom

    1 h-index

    2 publications

    952 citations

1–8 of 9

Venues

  1. arXiv (Cornell University)

    Repository · 2 publications · 34 citations

    2

    h-index

  2. Nature

    1 publications · 476 citations

    1

    h-index

1–2