dnn_6_BN.py 文件源码

def Q_func(self, state, train=True):

        test = not train

        s = Variable(state)
        h = F.tanh(self.bn1(self.fc1(s),test=test))
        h = F.tanh(self.bn2(self.fc2(h),test=test))  
        h = F.tanh(self.bn3(self.fc3(h),test=test))
        h = F.tanh(self.bn4(self.fc4(h),test=test))
        h = F.tanh(self.bn5(self.fc5(h),test=test))
        Q = self.q_value(h)

        return Q