Concepedia

Reinforcement Learning Transfer

Reinforcement Learning Transfer is a transfer learning methodology that leverages knowledge acquired in one or more source reinforcement learning tasks to improve learning efficiency, performance, or generalization in a distinct but related target reinforcement learning task.

561

Publications

34.7K

Citations

2K

Authors

546

Institutions

Publications per year

2017–2026

426

Parents

Publications

561

Learning dexterous in-hand manipulation

OpenAI Marcin Andrychowicz, Bowen Baker, Maciek Chociej et al. · The International Journal of Robotics Research · 2019 · 1.6K citations · Full text

, , +17

Transfer Learning for Reinforcement Learning Domains: A Survey

Matthew E. Taylor, Peter Stone · Journal of Machine Learning Research · 2009 · 1.6K citations

, , +8

The Arcade Learning Environment: An Evaluation Platform for General Agents

Journal of Artificial Intelligence Research · 2013 · 1.1K citations · Full text

, , +12

Transfer Learning in Deep Reinforcement Learning: A Survey

Zhuangdi Zhu, Kaixiang Lin, Anil K. Jain et al. · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023 · 679 citations · Full text

, , +8

Reinforcement Learning with Hierarchies of Machines

Ronald Parr, Stuart Russell · 1997 · 616 citations

, , +11

1–5 of 561

Authors

2K

  1. PS
    Peter Stone

    The University of Texas at Austin, United States

    22 publications · 3.3K citations

    20

    h-index

  2. ME
    Matthew E. Taylor

    Washington State University, United States

    20 publications · 3.2K citations

    19

    h-index

  3. SL
    Sergey Levine

    University of California, Berkeley, United States

    8 publications · 533 citations

    8

    h-index

  4. PA
    Pieter Abbeel

    University of California, Berkeley, United States

    7 publications · 477 citations

    7

    h-index

  5. AH
    Anna Helena Reali Costa

    Universidade de São Paulo, Brazil

    7 publications · 486 citations

    7

    h-index

1–5 of 2K

Institutions

546

  1. The University of Texas at Austin

    Austin, United States

    26 h-index

    80 publications

    5.7K citations

  2. Google (United States)

    Mountain View, United States

    14 h-index

    72 publications

    4.6K citations

  3. University of California, Berkeley

    Berkeley, United States

    13 h-index

    37 publications

    4.1K citations

  4. Carnegie Mellon University

    Pittsburgh, United States

    12 h-index

    23 publications

    1.6K citations

  5. Massachusetts Institute of Technology

    Cambridge, United States

    11 h-index

    30 publications

    3K citations

  6. Tsinghua University

    Beijing, China

    10 h-index

    28 publications

    1.3K citations

  7. Zhejiang University

    Hangzhou, China

    10 h-index

    28 publications

    1.6K citations

  8. Nanyang Technological University

    Singapore, Singapore

    10 h-index

    18 publications

    814 citations

1–8 of 546

Venues

  1. arXiv (Cornell University)

    Repository · 103 publications · 5K citations

    33

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 12 publications · 751 citations

    11

    h-index

  3. IEEE Robotics and Automation Letters

    10 publications · 333 citations

    9

    h-index

  4. Knowledge-Based Systems

    7 publications · 270 citations

    7

    h-index

  5. The International Journal of Robotics Research

    IJRR · 5 publications · 2.2K citations

    5

    h-index

1–5