c6035419bcd9637fe43c48f4bc71a66310c275c7,contents/5_Deep_Q_Network/DQN_modified.py,DeepQNetwork,_build_net,#DeepQNetwork#,68

Before Change

        // ------------------ build target_net ------------------
        with tf.variable_scope("target_net"):
            // c_names(collections_names) are the collections to store variables
            c_names = ["target_net_params", tf.GraphKeys.GLOBAL_VARIABLES]
            self.q_next = build_layers(self.s_, c_names, n_l1, w_initializer, b_initializer)

        with tf.variable_scope("q_target"):
            q_target = self.r + self.gamma * tf.reduce_max(self.q_next, axis=1, name="Qmax_s_")    // shape=(None, )

After Change

            q_target = self.r + self.gamma * tf.reduce_max(self.q_next, axis=1, name="Qmax_s_")    // shape=(None, )
            self.q_target = tf.stop_gradient(q_target)
        with tf.variable_scope("q_eval"):
            a_indices = tf.stack([tf.range(tf.shape(self.a)[0], dtype=tf.int32), self.a], axis=1)
            self.q_eval_wrt_a = tf.gather_nd(params=self.q_eval, indices=a_indices)    // shape=(None, )
        with tf.variable_scope("loss"):
            self.loss = tf.reduce_mean(tf.squared_difference(self.q_target, self.q_eval_wrt_a, name="TD_error"))

Instances