Mastering the game of Go without human knowledge

@article{Silver2017MasteringTG,
  title={Mastering the game of Go without human knowledge},
  author={D. Silver and Julian Schrittwieser and K. Simonyan and Ioannis Antonoglou and Aja Huang and A. Guez and T. Hubert and L. Baker and Matthew Lai and A. Bolton and Yutian Chen and T. Lillicrap and F. Hui and L. Sifre and George van den Driessche and T. Graepel and Demis Hassabis},
  journal={Nature},
  year={2017},
  volume={550},
  pages={354-359}
}
  • D. Silver, Julian Schrittwieser, +14 authors Demis Hassabis
  • Published 2017
  • Medicine, Computer Science
  • Nature
  • A long-standing goal of artificial intelligence is an algorithm that learns, tabula rasa, superhuman proficiency in challenging domains. [...] Key Method AlphaGo becomes its own teacher: a neural network is trained to predict AlphaGo’s own move selections and also the winner of AlphaGo’s games. This neural network improves the strength of the tree search, resulting in higher quality move selection and stronger self-play in the next iteration. Starting tabula rasa, our new program AlphaGo Zero achieved…Expand Abstract
    3,910 Citations
    Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
    • 719
    • PDF
    Artificial intelligence: Learning to play Go from scratch
    • 29
    Mastering the game of Go with deep neural networks and tree search
    • 8,270
    • PDF
    Scaffolding Learning for the Novice Players of Go
    • 1
    Learning to Play the Chess Variant Crazyhouse Above World Champion Level With Deep Neural Networks and Human Data
    • 3
    • Highly Influenced
    • PDF
    Mastering board games
    • 1
    Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model
    • 187
    • PDF
    Warm-Start AlphaZero Self-Play Search Enhancements
    • 1
    • Highly Influenced
    • PDF

    References

    SHOWING 1-10 OF 68 REFERENCES
    Mastering the game of Go with deep neural networks and tree search
    • 8,270
    • PDF
    TD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
    • 768
    • PDF
    Bootstrapping from Game Tree Search
    • 54
    • PDF
    Deep Reinforcement Learning from Self-Play in Imperfect-Information Games
    • 145
    • PDF
    Training Deep Convolutional Neural Networks to Play Go
    • 148
    • PDF
    Human-level control through deep reinforcement learning
    • 11,326
    • PDF