ChengTsang

Results 2 repositories owned by ChengTsang

This code is based on the implementation of http://www.cs.cmu.edu/afs/cs/Web/People/sandholm/potential-aware_imperfect-recall.aaai14.pdf, you can read it to understand its details.

Implement PPO-clip and PPO-penalty on Atari, which is the only open source of PPO-penalty