Temporal-difference Learning

Temporal-Difference Learning is a model-free reinforcement learning method that combines features of Monte Carlo methods and dynamic programming by updating value estimates based on the difference between temporally successive predictions, enabling learning from incomplete episodes through bootstrapping.

495

Publications

43.6K

Citations

1.1K

Authors

443

Institutions

Publications per year

2017–2026

169

Authors

1.1K

  1. RS
    Richard S. Sutton

    University of Alberta, Canada

    30 publications · 10.2K citations

    22

    h-index

  2. PS
    Peter Stone

    The University of Texas at Austin, United States

    12 publications · 1K citations

    12

    h-index

  3. DP
    Doina Precup

    McGill University, Canada

    10 publications · 2.1K citations

    10

    h-index

  4. DS
    David Silver

    Google DeepMind (United Kingdom), United Kingdom

    10 publications · 1.3K citations

    10

    h-index

  5. SM
    Shie Mannor

    Technion – Israel Institute of Technology, Israel

    11 publications · 1.2K citations

    10

    h-index

1–5 of 1.1K

Venues

  1. arXiv (Cornell University)

    Repository · 68 publications · 2.3K citations

    25

    h-index

  2. Proceedings of the AAAI Conference on Artificial Intelligence

    Conference · 11 publications · 1.1K citations

    10

    h-index

  3. Neural Computation

    9 publications · 1.4K citations

    9

    h-index

  4. 9

    h-index

  5. Machine Learning

    11 publications · 8.5K citations

    9

    h-index

1–5