rl_tuner.py 文件源码

def save_stored_rewards(self, file_name):
    """Saves the models stored rewards over time in a .npz file.

    Args:
      file_name: Name of the file that will be saved.
    """
    training_epochs = len(self.rewards_batched) * self.output_every_nth
    filename = os.path.join(self.output_dir,
                            file_name + '-' + str(training_epochs))
    np.savez(filename,
             train_rewards=self.rewards_batched,
             train_music_theory_rewards=self.music_theory_rewards_batched,
             train_note_rnn_rewards=self.note_rnn_rewards_batched,
             eval_rewards=self.eval_avg_reward,
             eval_music_theory_rewards=self.eval_avg_music_theory_reward,
             eval_note_rnn_rewards=self.eval_avg_note_rnn_reward,
             target_val_list=self.target_val_list)