Meta-learning For Transfer

Meta-Learning for Transfer is a meta-learning approach that enables agents to acquire generalized learning strategies across simulated environments such that rapid adaptation to real-world dynamics is achieved with minimal retraining.

64

Publications

4.4K

Citations

264

Authors

103

Institutions

Publications per year

2017–2026

63

Authors

264

  1. AG
    Alberto García-Durán

    École Polytechnique Fédérale de Lausanne, Switzerland

    2 publications · 33 citations

    2

    h-index

  2. AD
    Andreas Damianou

    University of Sheffield, United Kingdom

    2 publications · 56 citations

    2

    h-index

  3. SS
    Sargur Srihari

    University at Buffalo, State University of New York, United States

    2 publications · 60 citations

    2

    h-index

  4. YL
    Yaoyao Liu

    Max Planck Institute for Informatics, Germany

    2 publications · 1.3K citations

    2

    h-index

  5. MV
    Michael Volpp

    Robert Bosch (Taiwan), Taiwan

    2 publications · 26 citations

    2

    h-index

1–5 of 264

Venues

  1. arXiv (Cornell University)

    Repository · 13 publications · 365 citations

    11

    h-index

  2. Mechanical Systems and Signal Processing

    MSSP · 3 publications · 299 citations

    3

    h-index

  3. Knowledge-Based Systems

    3 publications · 240 citations

    3

    h-index

  4. Pattern Recognition

    2 publications · 67 citations

    2

    h-index

  5. Reliability Engineering & System Safety

    2 publications · 296 citations

    2

    h-index

1–5