atari_1step_qlearning.py 文件源码

def build_summaries():
    episode_reward = tf.Variable(0.)
    scalar_summary("Reward", episode_reward)
    episode_ave_max_q = tf.Variable(0.)
    scalar_summary("Qmax Value", episode_ave_max_q)
    logged_epsilon = tf.Variable(0.)
    scalar_summary("Epsilon", logged_epsilon)
    # Threads shouldn't modify the main graph, so we use placeholders
    # to assign the value of every summary (instead of using assign method
    # in every thread, that would keep creating new ops in the graph)
    summary_vars = [episode_reward, episode_ave_max_q, logged_epsilon]
    summary_placeholders = [tf.placeholder("float")
                            for i in range(len(summary_vars))]
    assign_ops = [summary_vars[i].assign(summary_placeholders[i])
                  for i in range(len(summary_vars))]
    summary_op = merge_all_summaries()
    return summary_placeholders, assign_ops, summary_op