This repository contains the implementation of two RL algorithms: Proximal Policy Optimization and Deep Q Learning both from scratch (with PyTorch) and using the TorchRL library.
The environment is the car racing simulation from OpenAI's Gym package.
Create a virtual environment:
conda create -n NAME_OF_THE_ENVIRONEMNT python=3.8
conda activate NAME_OF_THE_ENVIRONEMNT
Clone the repository:
git clone https://github.com/bielnebot/rl_implementations.git
And install the requirements:
pip install -r requirements.txt
- PPO with TorchRL
- DQN with TorchRL
- DQN from scratch
- PPO from scratch