- OpenAI Tensorflow code: https://github.com/openai/baselines/tree/master/baselines/ppo2
- https://github.com/ikostrikov/pytorch-a2c-ppo-acktr
To run training:
python trainer_plus.py
Comparison between OpenAI implementation and this implementation in Atari game BreakOut
:
The Pytorch implementation is much cleaner and runs a bit faster in terms of wall-clock time, yet still achieve comparable performance in the BreakOut
environment.