Exploration Bonuses

Exploration Bonuses is a reinforcement learning strategy that augments estimated action values with an additional term incentivizing the selection of less-visited states or actions, thereby promoting systematic exploration in sequential decision-making environments.

28

Publications

3.5K

Citations

91

Authors

37

Institutions

Publications per year

2017–2026

18

Variants

Exploration Bonus

Authors

91

  1. MG
    Marc G. Bellemare

    Google (United States), United States

    8 publications · 1.5K citations

    8

    h-index

  2. MC
    Marlos C. Machado

    University of Alberta, Canada

    4 publications · 165 citations

    4

    h-index

  3. GO
    Georg Ostrovski

    Google DeepMind (United Kingdom), United Kingdom

    4 publications · 1.3K citations

    4

    h-index

  4. RM
    Rémi Munos

    Google (United States), United States

    3 publications · 639 citations

    3

    h-index

  5. AV
    Aäron van den Oord

    Google (United States), United States

    2 publications · 392 citations

    2

    h-index

1–5 of 91

Venues

  1. arXiv (Cornell University)

    Repository · 11 publications · 1.5K citations

    11

    h-index

  2. Machine Learning

    2 publications · 165 citations

    2

    h-index

  3. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 2 publications · 37 citations

    2

    h-index

  4. Neural Information Processing Systems

    Conference · 2 publications · 701 citations

    2

    h-index

  5. International Conference on Machine Learning

    Conference · 2 publications · 189 citations

    2

    h-index

1–5