Concepedia

Sparse Reward Learning

Sparse Reward Learning is a reinforcement learning paradigm characterized by infrequent and limited feedback signals, where the agent must learn effective policies from rewards that are sparsely distributed in time and often binary or zero except upon task completion.

167

Publications

6.9K

Citations

657

Authors

179

Institutions

Publications per year

2017–2026

162

Variants

Sparse Reward Reinforcement Learning

Parents

Publications

167

Hindsight Experience Replay

Marcin Andrychowicz, Filip Wolski, Alex Ray et al. · arXiv (Cornell University) · 2017 · 352 citations · Full text

, , +15

Modular Multitask Reinforcement Learning with Policy Sketches

Jacob Andreas, Dan Klein, Sergey Levine · arXiv (Cornell University) · 2016 · 229 citations · Full text

, , +15

Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables

Kate Rakelly, Aurick Zhou, Deirdre Quillen et al. · arXiv (Cornell University) · 2019 · 228 citations · Full text

, , +13

Deep-Reinforcement-Learning-Based Autonomous UAV Navigation With Sparse Rewards

Chao Wang, Jian Wang, Jingjing Wang et al. · IEEE Internet of Things Journal · 2020 · 206 citations

, , +17

Stochastic Neural Networks for Hierarchical Reinforcement Learning

Carlos Florensa, Yan Duan, Pieter Abbeel · arXiv (Cornell University) · 2017 · 196 citations · Full text

, , +16

1–5 of 167

Authors

657

  1. SL
    Sergey Levine

    University of California, Berkeley, United States

    11 publications · 958 citations

    11

    h-index

  2. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    7 publications · 789 citations

    7

    h-index

  3. MN
    Mohammad Norouzi

    Google (United States), United States

    4 publications · 112 citations

    4

    h-index

  4. UT
    Ufuk Topcu

    The University of Texas at Austin, United States

    4 publications · 133 citations

    4

    h-index

  5. CF
    Chelsea Finn

    University of California, Berkeley, United States

    4 publications · 374 citations

    4

    h-index

1–5 of 657

Institutions

179

  1. Google (United States)

    Mountain View, United States

    11 h-index

    38 publications

    2.1K citations

  2. University of California, Berkeley

    Berkeley, United States

    10 h-index

    26 publications

    2.6K citations

  3. The University of Texas at Austin

    Austin, United States

    9 h-index

    23 publications

    819 citations

  4. Tsinghua University

    Beijing, China

    6 h-index

    22 publications

    1.2K citations

  5. Nanyang Technological University

    Singapore, Singapore

    5 h-index

    8 publications

    257 citations

  6. Chinese Academy of Sciences

    Beijing, China

    5 h-index

    22 publications

    577 citations

  7. University of Science and Technology of China

    Hefei, China

    5 h-index

    13 publications

    575 citations

  8. Universität Hamburg

    Hamburg, Germany

    4 h-index

    13 publications

    224 citations

1–8 of 179

Venues

  1. arXiv (Cornell University)

    Repository · 66 publications · 3.2K citations

    28

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 6 publications · 153 citations

    6

    h-index

  3. 5

    h-index

  4. IEEE Internet of Things Journal

    4 publications · 334 citations

    4

    h-index

  5. Sensors

    4 publications · 144 citations

    4

    h-index

1–5