Tensorflow-DPPO

self implementation of DPPO, Distributed Proximal Policy Optimization, by using tensorflow

the loss calculation is used from OPENAI PPO. the Distributed architecture design is inspired from Deepmind paper.

Name		Name	Last commit message	Last commit date
Latest commit History 21 Commits
Others		Others
Chief.py		Chief.py
DPPO.png		DPPO.png
Model.py		Model.py
PPO.py		PPO.py
README.md		README.md
Worker.py		Worker.py
main.py		main.py

Provide feedback