async_dqn.py 文件源码

def create_architecture(self):
        self.vars.sequence_length = tf.placeholder(tf.int64, [1], name="sequence_length")
        fc_input = self.get_input_layers()

        fc1 = layers.fully_connected(fc_input, self.fc_units_num, scope=self._name_scope + "/fc1")
        fc1_reshaped = tf.reshape(fc1, [1, -1, self.fc_units_num])

        self.recurrent_cells = self._get_ru_class()(self._recurrent_units_num)
        state_c = tf.placeholder(tf.float32, [1, self.recurrent_cells.state_size.c], name="initial_lstm_state_c")
        state_h = tf.placeholder(tf.float32, [1, self.recurrent_cells.state_size.h], name="initial_lstm_state_h")
        self.vars.initial_network_state = LSTMStateTuple(state_c, state_h)
        rnn_outputs, self.ops.network_state = tf.nn.dynamic_rnn(self.recurrent_cells,
                                                                fc1_reshaped,
                                                                initial_state=self.vars.initial_network_state,
                                                                sequence_length=self.vars.sequence_length,
                                                                scope=self._name_scope)
        reshaped_rnn_outputs = tf.reshape(rnn_outputs, [-1, self._recurrent_units_num])
        q = layers.linear(reshaped_rnn_outputs, num_outputs=self.actions_num, scope=self._name_scope + "/q")
        self.reset_state()
        return q