Mastering the game of Go with deep neural networks and tree search

@article{Silver2016MasteringTG,
  title={Mastering the game of Go with deep neural networks and tree search},
  author={David Silver and Aja Huang and Chris J. Maddison and Arthur Guez and Laurent Sifre and George van den Driessche and Julian Schrittwieser and Ioannis Antonoglou and Vedavyas Panneershelvam and Marc Lanctot and Sander Dieleman and Dominik Grewe and John Nham and Nal Kalchbrenner and Ilya Sutskever and Timothy P. Lillicrap and Madeleine Leach and Koray Kavukcuoglu and Thore Graepel and Demis Hassabis},
  journal={Nature},
  year={2016},
  volume={529},
  pages={484-489}
}
  • David Silver, Aja Huang, +17 authors Demis Hassabis
  • Published in Nature 2016
  • Computer Science, Medicine
  • Highlight Information
    The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. [...] Key Method Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this…Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 4,846 CITATIONS

    Accelerating and Improving AlphaZero Using Population Based Training

    VIEW 13 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero

    VIEW 12 EXCERPTS
    CITES BACKGROUND
    HIGHLY INFLUENCED

    Exploring the Performance of Deep Residual Networks in Crazyhouse Chess

    VIEW 7 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Building Evaluation Functions for Chess and Shogi with Uniformity Regularization Networks

    VIEW 4 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    Human-Like Playtesting with Deep Learning

    VIEW 4 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Inductive Logic Programming

    VIEW 7 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    Neural Information Processing

    VIEW 14 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Revisiting the Master-Slave Architecture in Multi-Agent Deep Reinforcement Learning

    VIEW 9 EXCERPTS
    CITES METHODS & BACKGROUND
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2000
    2020

    CITATION STATISTICS

    • 246 Highly Influenced Citations

    • Averaged 1,362 Citations per year from 2017 through 2019

    • 15% Increase in citations per year in 2019 over 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 10 REFERENCES

    Reinforcement Learning: An Introduction. Second

    • Richard S. Sutton, Andrew G. Barto
    • 2018
    VIEW 1 EXCERPT

    British Go Association. An Introduction to Go

    • 2017

    Mastering the game of Go without human knowledge

    VIEW 1 EXCERPT

    Artificial intelligence: Google’s AlphaGo beats Go master Lee Se-dol

    • BBC News
    • Mar.
    • 2016
    VIEW 1 EXCERPT

    Where does AlphaGo go: from church-turing thesis to AlphaGo thesis and beyond

    VIEW 1 EXCERPT

    A brief introduction of AlphaGo and Deep Learning: How it works

    • Henry