Improved Feature Learning: A Maximum-Average-Out Deep Neural Network for the Game Go

Table 1

Computer configuration.

Toolkit package	CNTK 2.7
Runtime	.Net 4.7.2
OS	Windows 10
CPU	AMD [email protected] GHz
RAM	32 GB
GPU	RTX2070
Threads used	16
Development environment	Visual studio 2017 community
Communicate environment	GTP + sabaki v0.43.3
Optimization function	Stochastic gradient descent (SGD)
Learning rate	0.001
Minibatch	128
Epoch	10