Learning From Sparse Rewards

Learning From Sparse Rewards is a reinforcement learning paradigm in which an agent must acquire optimal behavior from infrequent and minimal feedback signals, distinguished by the scarcity of reward occurrences relative to the duration and complexity of the task.

188

Publications

10K

Citations

692

Authors

201

Institutions

Publications per year

2017–2026

176

Authors

692

  1. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    14 publications · 1.2K citations

    13

    h-index

  2. SL
    Sergey Levine

    University of California, Berkeley, United States

    8 publications · 497 citations

    8

    h-index

  3. NH
    Nicolas Heess

    Google (United States), United States

    7 publications · 1.3K citations

    7

    h-index

  4. TL
    Timothy Lillicrap

    Google (United States), United States

    5 publications · 757 citations

    5

    h-index

  5. AG
    Abhishek Gupta

    University of California, Berkeley, United States

    5 publications · 161 citations

    5

    h-index

1–5 of 692

Venues

  1. arXiv (Cornell University)

    Repository · 85 publications · 4.6K citations

    34

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 10 publications · 188 citations

    9

    h-index

  3. 6

    h-index

  4. International Conference on Machine Learning

    Conference · 4 publications · 370 citations

    4

    h-index

  5. International Conference on Learning Representations

    Conference · 3 publications · 286 citations

    3

    h-index

1–5