Corpus ID: 13882525

Temporal Coherence and Prediction Decay in TD Learning

@inproceedings{Beal1999TemporalCA,
  title={Temporal Coherence and Prediction Decay in TD Learning},
  author={D. F. Beal and M. Smith},
  booktitle={IJCAI},
  year={1999}
}
  • D. F. Beal, M. Smith
  • Published in IJCAI 1999
  • Computer Science
  • This paper describes improvements to the temporal difference TD(λ) learning method. The standard form of the TD(λ) method has the problem that two control parameters, learning rate and temporal discount, need to be chosen appropriately. These parameters can have a major effect on performance, particularly the learning rate parameter, which affects the stability of the process as well as the number of observations required. Our extension to the TD(λ) algorithm automatically sets and subsequently… CONTINUE READING
    17 Citations
    Temporal Coherence in TD-Learning for Strategic Board Games Case Study Report
    • Highly Influenced
    • PDF
    Online Adaptable Learning Rates for the Game Connect-4
    • 15
    • PDF
    Temporal difference learning with eligibility traces for the game connect four
    • 16
    • PDF
    Mastering 2048 With Delayed Temporal Coherence Learning, Multistage Weight Promotion, Redundant Encoding, and Carousel Shaping
    • 16
    • PDF
    General Board Game Playing for Education and Research in Generic AI Game Learning
    • W. Konen
    • Computer Science, Mathematics
    • 2019 IEEE Conference on Games (CoG)
    • 2019
    • 6
    • PDF
    Learning of Piece Values for Chess Variants
    • 3
    • Highly Influenced
    • PDF
    Partial order bounding: A new approach to evaluation in game tree search
    • M. Müller
    • Mathematics, Computer Science
    • Artif. Intell.
    • 2001
    • 15
    • PDF
    Learning the Piece Values for Three Chess Variants
    • 12
    • Highly Influenced
    • PDF

    References

    SHOWING 1-8 OF 8 REFERENCES
    Increased rates of convergence through learning rate adaptation
    • 1,922
    On-Line Step Size Adaptation, Technical Report RT07/97 INESC
    • Rua Alves Redol,
    • 1998
    Temporal Difference Learning for Heuristic Domains
    • JCIS'98 Proceedings Vol(l)
    • 1998
    Learning Piece Values Using Temporal Differences
    • 46
    On step-size and bias in temporal-difference learning
    • Proceedings of the Eighth Yale Workshop on Adaptive and Learning Systems
    • 1994
    On-Line Step Size Adaptation
    • On-Line Step Size Adaptation
    • 1000