5135e42987c9a6349e3c198fabdb939774d21fbb,contents/10_A3C/A3C_continuous_action.py,ACNet,__init__,#ACNet#Any#Any#,45

Before Change

                with tf.name_scope("a_loss"):
                    log_prob = normal_dist.log_prob(self.a_his)
                    exp_v = log_prob * td
                    entropy = normal_dist.entropy()  // encourage exploration
                    self.exp_v = ENTROPY_BETA * entropy + exp_v
                    self.a_loss = tf.reduce_mean(-self.exp_v)

                with tf.name_scope("choose_a"):  // use local params to choose action
                    self.A = tf.clip_by_value(tf.squeeze(normal_dist.sample(1), axis=0), A_BOUND[0], A_BOUND[1])
                with tf.name_scope("local_grad"):
                    self.a_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=scope + "/actor")
                    self.c_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=scope + "/critic")
                    self.a_grads = tf.gradients(self.a_loss, self.a_params)
                    self.c_grads = tf.gradients(self.c_loss, self.c_params)

            with tf.name_scope("sync"):
                with tf.name_scope("pull"):
                    self.pull_a_params_op = [l_p.assign(g_p) for l_p, g_p in zip(self.a_params, globalAC.a_params)]
                    self.pull_c_params_op = [l_p.assign(g_p) for l_p, g_p in zip(self.c_params, globalAC.c_params)]
                with tf.name_scope("push"):
                    self.update_a_op = OPT_A.apply_gradients(zip(self.a_grads, globalAC.a_params))
                    self.update_c_op = OPT_C.apply_gradients(zip(self.c_grads, globalAC.c_params))

    def _build_net(self ):

After Change

                with tf.name_scope("a_loss"):
                    log_prob = normal_dist.log_prob(self.a_his)
                    exp_v = log_prob * td
                    entropy = tf.stop_gradient(normal_dist.entropy())  // encourage exploration
                    self.exp_v = ENTROPY_BETA * entropy + exp_v
                    self.a_loss = tf.reduce_mean(-self.exp_v)

                with tf.name_scope("choose_a"):  // use local params to choose action
                    self.A = tf.clip_by_value(tf.squeeze(normal_dist.sample(1), axis=0), A_BOUND[0], A_BOUND[1])
                with tf.name_scope("local_grad"):
                    self.a_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=scope + "/actor")
                    self.c_params = tf.get_collection(tf.GraphKeys.TRAINABLE_VARIABLES, scope=scope + "/critic")
                    self.a_grads = tf.gradients(self.a_loss, self.a_params)
                    self.c_grads = tf.gradients(self.c_loss, self.c_params)

            with tf.name_scope("sync"):
                with tf.name_scope("pull"):
                    self.pull_a_params_op = [l_p.assign(g_p) for l_p, g_p in zip(self.a_params, globalAC.a_params)]
                    self.pull_c_params_op = [l_p.assign(g_p) for l_p, g_p in zip(self.c_params, globalAC.c_params)]
                with tf.name_scope("push"):
                    self.update_a_op = OPT_A.apply_gradients(zip(self.a_grads, globalAC.a_params))
                    self.update_c_op = OPT_C.apply_gradients(zip(self.c_grads, globalAC.c_params))

    def _build_net(self):

Instances