• Computer Science
  • Published in ICML 2014

Training Deep Convolutional Neural Networks to Play Go

@article{Clark2014TrainingDC,
  title={Training Deep Convolutional Neural Networks to Play Go},
  author={Christopher Clark and Amos J. Storkey},
  journal={ArXiv},
  year={2014},
  volume={abs/1412.3409}
}
Mastering the game of Go has remained a longstanding challenge to the field of AI. Modern computer Go programs rely on processing millions of possible future positions to play well, but intuitively a stronger and more 'humanlike' way to play the game would be to rely on pattern recognition rather than brute force computation. Following this sentiment, we train deep convolutional neural networks to play Go by training them to predict the moves made by expert Go players. To solve this problem we… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 100 CITATIONS, ESTIMATED 96% COVERAGE

Non-Parametric Transformation Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Deep neural network analysis of go games: which stones motivate a move?

VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Learning to Play Stratego with Convolutional Neural Networks

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Low-resource learning in complex games

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Playing Go without Game Tree Search Using Convolutional Neural Networks

VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Human-Like Playtesting with Deep Learning

  • 2018 IEEE Conference on Computational Intelligence and Games (CIG)
  • 2018
VIEW 3 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Move Prediction Using Deep Convolutional Neural Networks in Hex

  • IEEE Transactions on Games
  • 2018
VIEW 4 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2015
2019

CITATION STATISTICS

  • 13 Highly Influenced Citations

  • Averaged 21 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 14 REFERENCES

Fuego—An Open-Source Framework for Board Games and Go Engine Based on Monte Carlo Tree Search

  • IEEE Transactions on Computational Intelligence and AI in Games
  • 2010
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Move Prediction in Go with the Maximum Entropy Method

  • 2007 IEEE Symposium on Computational Intelligence and Games
  • 2007
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Comparison of Bayesian move prediction systems for Computer Go

  • 2012 IEEE Conference on Computational Intelligence and Games (CIG)
  • 2012
VIEW 1 EXCERPT

Current Frontiers in Computer Go

  • IEEE Transactions on Computational Intelligence and AI in Games
  • 2010
VIEW 2 EXCERPTS

Curriculum learning

Bengio, Yoshua, +5 authors Jason
  • In ICML,
  • 2009
VIEW 1 EXCERPT