Extended Data Table 3 Supervised learning results for the policy network

From: Mastering the game of Go with deep neural networks and tree search

  1. The policy network architecture consists of 128, 192 or 256 filters in convolutional layers; an explicit symmetry ensemble over 2, 4 or 8 symmetries; using only the first 4, 12 or 20 input feature planes listed in Extended Data Table 1. The results consist of the test and train accuracy on the KGS data set; and the percentage of games won by given policy network against AlphaGo’s policy network (highlighted row 2): using the policy networks to select moves directly (raw wins); or using AlphaGo’s search to select moves (AlphaGo wins); and finally the computation time for a single evaluation of the policy network.
Back to article page