Derk3: Open submission and potential baseline

Dr. Derks Mutant Battlegrounds
5

I ran your code. Training goes well :+1: :+1:

In my case, I am training my agent using ‘IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures’ of DeepMind.

Thank you for your baseline code. I want to share my code soon after getting an appropriate performance.