Predicting expert moves in the game of Othello using fully convolutional neural networks

Careful feature engineering is an important factor of artificial intelligence for games. In this paper the benefit of delegating the engineering efforts to the model rather than the features are investigated using the board game Othello as a case study. The main result is that using a raw board state representation, an 11-layer convolutional neural network can be trained to achieve 57.4% prediction accuracy on a test set, surpassing previous state of the art in this task. The accuracy is increased to 58.3% by adding several common handcrafted features as input to the network but at the cost of more than half again as much the computation time.