An implementation of a go (baduk) AI, following methods published for AlphaGo Zero. The primary purpose is to gain hands-on experience with machine learning.
Batch norm is implemented for the convolutional block, the residual block, and the policy head. It needs to be implemented for the value head. Also consider removing biases from layers preceding batch norm.
Batch norm is implemented for the convolutional block, the residual block, and the policy head. It needs to be implemented for the value head. Also consider removing biases from layers preceding batch norm.