rollout.py 文件源码

def update_recurrent_unit(self):
        # Weights and Bias for input and hidden tensor
        self.Wi = self.update_rate * self.Wi + (1 - self.update_rate) * tf.identity(self.lstm.Wi)
        self.Ui = self.update_rate * self.Ui + (1 - self.update_rate) * tf.identity(self.lstm.Ui)
        self.bi = self.update_rate * self.bi + (1 - self.update_rate) * tf.identity(self.lstm.bi)

        self.Wf = self.update_rate * self.Wf + (1 - self.update_rate) * tf.identity(self.lstm.Wf)
        self.Uf = self.update_rate * self.Uf + (1 - self.update_rate) * tf.identity(self.lstm.Uf)
        self.bf = self.update_rate * self.bf + (1 - self.update_rate) * tf.identity(self.lstm.bf)

        self.Wog = self.update_rate * self.Wog + (1 - self.update_rate) * tf.identity(self.lstm.Wog)
        self.Uog = self.update_rate * self.Uog + (1 - self.update_rate) * tf.identity(self.lstm.Uog)
        self.bog = self.update_rate * self.bog + (1 - self.update_rate) * tf.identity(self.lstm.bog)

        self.Wc = self.update_rate * self.Wc + (1 - self.update_rate) * tf.identity(self.lstm.Wc)
        self.Uc = self.update_rate * self.Uc + (1 - self.update_rate) * tf.identity(self.lstm.Uc)
        self.bc = self.update_rate * self.bc + (1 - self.update_rate) * tf.identity(self.lstm.bc)

        def unit(x, hidden_memory_tm1):
            previous_hidden_state, c_prev = tf.unpack(hidden_memory_tm1)

            # Input Gate
            i = tf.sigmoid(
                tf.matmul(x, self.Wi) +
                tf.matmul(previous_hidden_state, self.Ui) + self.bi
            )

            # Forget Gate
            f = tf.sigmoid(
                tf.matmul(x, self.Wf) +
                tf.matmul(previous_hidden_state, self.Uf) + self.bf
            )

            # Output Gate
            o = tf.sigmoid(
                tf.matmul(x, self.Wog) +
                tf.matmul(previous_hidden_state, self.Uog) + self.bog
            )

            # New Memory Cell
            c_ = tf.nn.tanh(
                tf.matmul(x, self.Wc) +
                tf.matmul(previous_hidden_state, self.Uc) + self.bc
            )

            # Final Memory cell
            c = f * c_prev + i * c_

            # Current Hidden state
            current_hidden_state = o * tf.nn.tanh(c)

            return tf.pack([current_hidden_state, c])

        return unit