Learning to Predict by the Methods of Temporal Differences

@article{Sutton2005LearningTP,
  title={Learning to Predict by the Methods of Temporal Differences},
  author={Richard S. Sutton},
  journal={Machine Learning},
  year={2005},
  volume={3},
  pages={9-44}
}
  • Richard S. Sutton
  • Published 2005
  • Computer Science
  • Machine Learning
  • This article introduces a class of incremental learning procedures specialized for prediction – that is, for using past experience with an incompletely known system to predict its future behavior. [...] Key Result We argue that most problems to which supervised learning is currently applied are really prediction problems of the sort to which temporal-difference methods can be applied to advantage.Expand Abstract

    Figures and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 2,773 CITATIONS

    On the Worst-Case Analysis of Temporal-Difference Learning Algorithms

    VIEW 6 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Temporal-Difference Networks

    VIEW 1 EXCERPT
    CITES METHODS

    Predicting Periodicity with Temporal Difference Learning

    VIEW 1 EXCERPT
    CITES METHODS

    Practical issues in temporal difference learning

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Learning to Predict Independent of Span

    VIEW 4 EXCERPTS
    CITES BACKGROUND

    FILTER CITATIONS BY YEAR

    1988
    2020

    CITATION STATISTICS

    • 241 Highly Influenced Citations

    • Averaged 224 Citations per year from 2018 through 2020