Noisy Exploration

Noisy Exploration is a stochastic exploration strategy in reinforcement learning where randomness is explicitly injected into the action selection process to facilitate exploration, distinguishing it from deterministic or purely optimistic exploration methods by relying on probabilistic perturbations of policies or value estimates.

18

Publications

2.1K

Citations

58

Authors

29

Institutions

Publications per year

2017–2026

10

Authors

58

  1. PD
    Prafulla Dhariwal

    OpenAI (United States), United States

    2 publications · 463 citations

    2

    h-index

  2. TA
    Tamim Asfour

    Karlsruhe Institute of Technology, Germany

    2 publications · 463 citations

    2

    h-index

  3. MA
    Marcin Andrychowicz

    Google (United States), United States

    2 publications · 463 citations

    2

    h-index

  4. MP
    Matthias Plappert

    OpenAI (United States), United States

    2 publications · 463 citations

    2

    h-index

  5. ES
    Eric Schulz

    University College London, United Kingdom

    2 publications · 203 citations

    2

    h-index

1–5 of 58

Venues

  1. arXiv (Cornell University)

    Repository · 4 publications · 456 citations

    4

    h-index

  2. Journal of Machine Learning Research

    JMLR · 1 publications · 56 citations

    1

    h-index

  3. bioRxiv (Cold Spring Harbor Laboratory)

    Repository · 1 publications · 35 citations

    1

    h-index

  4. Research in Economics

    1 publications · 12 citations

    1

    h-index

  5. IEEE Transactions on Robotics and Automation

    1 publications · 274 citations

    1

    h-index

1–5