actor_learner.py 文件源码

def setup_summaries(self):
        episode_reward = tf.Variable(0.)
        s1 = tf.scalar_summary("Episode Reward " + str(self.actor_id), episode_reward)
        if self.alg_type == "a3c":
            summary_vars = [episode_reward]
        else:
            episode_ave_max_q = tf.Variable(0.)
            s2 = tf.scalar_summary("Max Q Value " + str(self.actor_id), episode_ave_max_q)
            logged_epsilon = tf.Variable(0.)
            s3 = tf.scalar_summary("Epsilon " + str(self.actor_id), logged_epsilon)
            summary_vars = [episode_reward, episode_ave_max_q, logged_epsilon]
        summary_placeholders = [tf.placeholder("float") for _ in range(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i]) for i in range(len(summary_vars))]
        with tf.control_dependencies(update_ops):
            summary_ops = tf.merge_all_summaries()
        return summary_placeholders, update_ops, summary_ops