Skip to content

Latest commit

 

History

History
4 lines (3 loc) · 369 Bytes

README.md

File metadata and controls

4 lines (3 loc) · 369 Bytes

RL-PPO-with-Unity

The implementation of PPO algorithm based on the Unity3d environment.

We use ml-agents to connect Unity game environment with learning algorithm based on python runtime. In the training and inference stage, we use TensorFlow to build our neural network.