Improved Online Sequential Extreme Learning Machine: A New Intelligent Evaluation Method for AZ-Style Algorithms

@article{Li2019ImprovedOS,
  title={Improved Online Sequential Extreme Learning Machine: A New Intelligent Evaluation Method for AZ-Style Algorithms},
  author={X. Li and S. He and Z. Wei and Licheng Wu},
  journal={IEEE Access},
  year={2019},
  volume={7},
  pages={124891-124901}
}
  • X. Li, S. He, +1 author Licheng Wu
  • Published 2019
  • Computer Science
  • IEEE Access
  • Researches on computer games for Go, Chess, and Japanese Chess stand out as one of the notable landmarks in the progress of artificial intelligence. AlphaGo, AlphaGo Zero, and AlphaZero algorithms, which are called AlphaZero style (AZ-style) algorithms in some literature [1], have achieved superhuman performance by using deep reinforcement learning (DRL). However, the unavailability of training details, expensive equipment used for model training, and the low evaluation accuracy resulted by… CONTINUE READING

    Figures, Tables, and Topics from this paper

    References

    SHOWING 1-10 OF 32 REFERENCES
    A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
    • 885
    • Highly Influential
    • PDF
    Mastering the game of Go without human knowledge
    • 3,918
    • Highly Influential
    • PDF
    Mastering the game of Go with deep neural networks and tree search
    • 8,279
    • PDF
    A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks
    • 1,454
    • PDF
    Extreme learning machine: Theory and applications
    • 7,790
    • PDF
    Extreme learning machine: a new learning scheme of feedforward neural networks
    • G. Huang, Qin-Yu Zhu, C. Siew
    • Computer Science
    • 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)
    • 2004
    • 2,886
    • PDF
    Extreme learning machine: RBF network case
    • G. Huang, C. Siew
    • Computer Science
    • ICARCV 2004 8th Control, Automation, Robotics and Vision Conference, 2004.
    • 2004
    • 245
    • PDF
    ELF: An Extensive, Lightweight and Flexible Research Platform for Real-time Strategy Games
    • 95
    • Highly Influential
    • PDF
    Temporal difference learning and TD-Gammon
    • 1,120
    Local Move Prediction in Go
    • 37