====== DQN ======

  * https://github.com/facebookresearch/rela
    * Facebook AI, DQN, ApeX, R2D2 구현
  * https://github.com/matthiasplappert/keras-rl
  * https://oshearesearch.com/index.php/2016/06/14/kerlym-a-deep-reinforcement-learning-toolbox-in-keras/


  * PER
    * https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/blob/master/contents/5.2_Prioritized_Replay_DQN/RL_brain.py


  * https://pytorch.org/tutorials/intermediate/reinforcement_q_learning.html

===== Rainbow =====

  * https://github.com/higgsfield/RL-Adventure
  * https://github.com/Shmuma/ptan/tree/master/samples/rainbow