Entropy-based Exploration

Entropy-Based Exploration is a reinforcement learning exploration strategy that uses the entropy of the policy distribution as a measure of uncertainty to encourage the agent to visit states and take actions that maximize information gain and reduce predictive uncertainty.

29

Publications

846

Citations

114

Authors

55

Institutions

Publications per year

2017–2026

17

Authors

114

  1. MT
    Marc Toussaint

    University of Stuttgart, Germany

    2 publications · 33 citations

    2

    h-index

  2. DS
    Dale Schuurmans

    University of Alberta, Canada

    2 publications · 62 citations

    2

    h-index

  3. KS
    Karan Singh

    Princeton University, United States

    2 publications · 106 citations

    2

    h-index

  4. SM
    Sham M. Kakade

    Microsoft (United States), United States

    2 publications · 106 citations

    2

    h-index

  5. JK
    Johannes Kulick

    University of Alabama in Huntsville, United States

    2 publications · 33 citations

    2

    h-index

1–5 of 114

Venues

  1. arXiv (Cornell University)

    Repository · 6 publications · 228 citations

    6

    h-index

  2. Sensors

    1 publications · 12 citations

    1

    h-index

  3. Frontiers in Neuroscience

    1 publications · 11 citations

    1

    h-index

  4. Environmental Research

    1 publications · 45 citations

    1

    h-index

  5. 1

    h-index

1–5