Skip to content

Latest commit

 

History

History
6 lines (5 loc) · 298 Bytes

README.md

File metadata and controls

6 lines (5 loc) · 298 Bytes
Raw

CarVerification

This project use PPO algorithm(based on TensorLayer) and Unity environment(ml-agents-envs release_12)to pretrain RL models to be put on the Raspicar.

Features

  • Based on Tensorlayer tutorial_PPO.py, add visual input
  • Based on Tensorlayer tutorial_PPO.py, add discrete action