dqn.py 文件源码

def setup_summary(self):
        episode_total_reward = tf.Variable(0.)
        tf.scalar_summary(ENV_NAME + '/Total Reward/Episode', episode_total_reward)
        episode_avg_max_q = tf.Variable(0.)
        tf.scalar_summary(ENV_NAME + '/Average Max Q/Episode', episode_avg_max_q)
        episode_duration = tf.Variable(0.)
        tf.scalar_summary(ENV_NAME + '/Duration/Episode', episode_duration)
        episode_avg_loss = tf.Variable(0.)
        tf.scalar_summary(ENV_NAME + '/Average Loss/Episode', episode_avg_loss)
        summary_vars = [episode_total_reward, episode_avg_max_q, episode_duration, episode_avg_loss]
        summary_placeholders = [tf.placeholder(tf.float32) for _ in xrange(len(summary_vars))]
        update_ops = [summary_vars[i].assign(summary_placeholders[i]) for i in xrange(len(summary_vars))]
        summary_op = tf.merge_all_summaries()
        return summary_placeholders, update_ops, summary_op