Predicting Moves in Chess using Convolutional Neural Networks
暂无分享,去创建一个
We used a three layer Convolutional Neural Network (CNN) to make move predictions in chess. The task was defined as a two-part classification problem: a piece-selector CNN is trained to score which white pieces should be made to move, and move-selector CNNs for each piece produce scores for where it should be moved. This approach reduced the intractable class space in chess by a square root. The networks were trained using 20,000 games consisting of 245,000 moves made by players with an ELO rating higher than 2000 from the Free Internet Chess Server. The piece-selector network was trained on all of these moves, and the move-selector networks trained on all moves made by the respective piece. Black moves were trained on by using a data augmentation to frame it as a move made by the
[1] A. Storkey,et al. Teaching Deep Convolutional Neural Networks to Play Go , 2014, ArXiv.
[2] Geoffrey E. Hinton,et al. Deep Learning , 2015 .
[3] Johannes Fürnkranz,et al. Machine Learning in Computer Chess: The Next Generation , 1996, J. Int. Comput. Games Assoc..
[4] Sebastian Thrun,et al. Learning to Play the Game of Chess , 1994, NIPS.