Move Evaluation in Go Using Deep Convolutional Neural Networks
Abstract
The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function. In this paper we investigate whether deep convolutional networks can be used to directly represent and learn this knowledge. We train a large 12-layer convolutional neural network by supervised learning from a database of human professional games. The network correctly predicts the expert move in 55% of positions, equalling the accuracy of a 6 dan human player. When the trained convolutional network was used directly to play games of Go, without any search, it beat the traditional search program GnuGo in 97% of games, and matched the performance of a state-of-the-art Monte-Carlo tree search that simulates a million positions per move.
Keywords
Cite
@article{arxiv.1412.6564,
title = {Move Evaluation in Go Using Deep Convolutional Neural Networks},
author = {Chris J. Maddison and Aja Huang and Ilya Sutskever and David Silver},
journal= {arXiv preprint arXiv:1412.6564},
year = {2015}
}
Comments
Minor edits and included captures in Figure 2