This is one naive RL algorithm repo, used to facilitate my future research and urge my own learning.

This repo is mainly modified from Spinning Up, Stable Baselines and Baselines. I will try to complete this repo using only Pytorch.

• PPO
• SAC
• More...

• Pytorch >= 1.5
• Python >= 3.6.1

git clone https://github.com/teslacool/RL-Algo-Zoo
cd RL-Algo-Zoo 
pip install -e .

python run.py