Concepedia

Sample-efficient Reinforcement Learning

Sample-Efficient Reinforcement Learning is a reinforcement learning approach that belongs to the class of methods designed to achieve high performance with minimal environmental interactions, distinguished by its focus on rapidly acquiring effective policies through optimized exploration, effective use of experience, and often leveraging prior knowledge or data-efficient learning strategies.

174

Publications

8.9K

Citations

565

Authors

134

Institutions

Publications per year

2017–2026

155

Variants

Sample-efficient Rl

Parents

Publications

174

CURL: Contrastive Unsupervised Representations for Reinforcement\n Learning

Aravind Srinivas, Michael Laskin, Pieter Abbeel · arXiv (Cornell University) · 2020 · 394 citations · Full text

, , +14

Is Q-learning Provably Efficient?

Chi Jin, Zeyuan Allen-Zhu, Sébastien Bubeck et al. · arXiv (Cornell University) · 2018 · 338 citations · Full text

, , +14

Learning to Adapt in Dynamic, Real-World Environments Through\n Meta-Reinforcement Learning

Anusha Nagabandi, Ignasi Clavera, Simin Liu et al. · arXiv (Cornell University) · 2018 · 300 citations · Full text

, , +17

Benchmarking Model-Based Reinforcement Learning

Tingwu Wang, Xuchan Bao, Ignasi Clavera et al. · arXiv (Cornell University) · 2019 · 242 citations · Full text

, , +12

Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction

Aviral Kumar, Justin Fu, George Tucker et al. · arXiv (Cornell University) · 2019 · 235 citations · Full text

, , +14

1–5 of 174

Authors

565

  1. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    13 publications · 1.5K citations

    12

    h-index

  2. SL
    Sergey Levine

    University of California, Berkeley, United States

    12 publications · 1.4K citations

    12

    h-index

  3. JL
    John Langford

    Microsoft (United States), United States

    6 publications · 171 citations

    6

    h-index

  4. AK
    Akshay Krishnamurthy

    Microsoft (United States), United States

    6 publications · 171 citations

    6

    h-index

  5. NJ
    Nan Jiang

    East China Jiaotong University, China

    5 publications · 145 citations

    5

    h-index

1–5 of 565

Institutions

134

  1. University of California, Berkeley

    Berkeley, United States

    16 h-index

    42 publications

    4K citations

  2. Google (United States)

    Mountain View, United States

    15 h-index

    45 publications

    3.9K citations

  3. Carnegie Mellon University

    Pittsburgh, United States

    12 h-index

    16 publications

    721 citations

  4. Microsoft Research (United Kingdom)

    Cambridge, United Kingdom

    6 h-index

    21 publications

    767 citations

  5. Tsinghua University

    Beijing, China

    6 h-index

    23 publications

    552 citations

  6. University of Cambridge

    Cambridge, United Kingdom

    6 h-index

    12 publications

    806 citations

  7. University of Illinois Urbana-Champaign

    Urbana, United States

    6 h-index

    7 publications

    190 citations

  8. University of Washington

    Seattle, United States

    6 h-index

    9 publications

    635 citations

1–8 of 134

Venues

  1. arXiv (Cornell University)

    Repository · 87 publications · 4.9K citations

    34

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 466 citations

    12

    h-index

  3. International Conference on Machine Learning

    Conference · 5 publications · 151 citations

    5

    h-index

  4. International Conference on Learning Representations

    Conference · 4 publications · 160 citations

    4

    h-index

  5. IEEE Robotics and Automation Letters

    3 publications · 306 citations

    3

    h-index

1–5