Count-based Exploration

Count-Based Exploration is a reinforcement learning exploration strategy that belongs to the class of intrinsic motivation methods, distinguished by its reliance on visitation frequency counts to quantify state novelty and direct agent behavior toward less-explored regions of the environment.

21

Publications

2.3K

Citations

56

Authors

18

Institutions

Publications per year

2017–2026

16

Authors

56

  1. HL
    Honglak Lee

    University of Michigan, United States

    7 publications · 274 citations

    7

    h-index

  2. YG
    Yijie Guo

    University of Michigan, United States

    7 publications · 274 citations

    7

    h-index

  3. MG
    Marc G. Bellemare

    Google (United States), United States

    6 publications · 1.4K citations

    6

    h-index

  4. MM
    Marcin Moczulski

    University of Oxford, United Kingdom

    5 publications · 107 citations

    5

    h-index

  5. MN
    Mohammad Norouzi

    Google (United States), United States

    5 publications · 107 citations

    5

    h-index

1–5 of 56

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 1K citations

    10

    h-index

  2. International Conference on Machine Learning

    Conference · 2 publications · 262 citations

    2

    h-index

  3. Neural Information Processing Systems

    Conference · 1 publications · 679 citations

    1

    h-index

  4. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 1 publications · 17 citations

    1

    h-index

  5. International Conference on Learning Representations

    Conference · 1 publications · 42 citations

    1

    h-index

1–5