MADDPG_Morvan_vector.py 文件源码

def learn_actor(self, s, x_ma, epoch):   # batch update
        _, police_grads = self.sess.run(self.train_ops, feed_dict={S: s, X_MA: x_ma})
        # the following method for soft replace target params is computational expansive
        # target_params = (1-tau) * target_params + tau * eval_params
        # self.sess.run([tf.assign(t, (1 - self.tau) * t + self.tau * e) for t, e in zip(self.t_params, self.e_params)])

        summary = tf.Summary()
        # summary.value.add(tag='info/c_gradient{}'.format(self.agent_id), simple_value=float(_c_grad))
        summary.value.add(tag='info/police_grads{}'.format(self.agent_id), simple_value=np.mean([np.mean(_) for _ in police_grads]))
        writer.add_summary(summary, epoch)
        writer.flush()

        # instead of above method, I use a hard replacement here
        if self.t_replace_counter % self.t_replace_iter == 0:
            self.sess.run([tf.assign(t, e) for t, e in zip(self.t_params, self.e_params)])
        self.t_replace_counter += 1