Move Evaluation in Go Using Deep Convolutional Neural Networks
This work addresses the problem of move evaluation in Go for AI systems, showing a significant performance leap over traditional methods.
The authors tackled the challenge of move evaluation in Go by training a deep convolutional neural network on professional games, achieving 55% accuracy in predicting expert moves and beating the traditional search program GnuGo in 97% of games without search.
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.