-
Playing atari pong game from openai Gym use Q-learning and experience replay memory [2].
-
The implementation base on Shubham Lohiya[1] and references from juliankappler [3]
-
Run
python play_pong.py
- [1] https://github.com/shubhlohiya/playing-atari-with-deep-RL
- [2] Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013).
- [3] https://github.com/juliankappler/lunar-lander