example.py 文件源码

def __call__(self, X):
        # generate random values
        R = np.random.randn(X.data.shape[0], self.rand_sz)
        R = Variable(R.astype("float32"))

        # attach random to the inputs
        h = F.concat([R, X])
        #h = R

        h = self.ipt(h)
        #h = F.dropout(h)
        y = self.out(h)

        # prior knowledge: environment observation is one - hot vector
        obs = F.softmax(y[:, :-2])
        # prior knowledge: reward is in [0,1]
        rew = F.sigmoid(y[:,[-2]])
        fin = F.sigmoid(y[:, [-1]])

        y = F.concat([obs, rew, fin])

        return y