Project used PyGame, PyTorch, and Stable Baselines 3. The RL algorithm of choice is Proximal Policy Optimization (PPO) and is successfully implemented in a perpendicular and parallel parking environment as seen below.
Make sure you have Anaconda locally installed. In order to install the necessary dependencies, run the following command
conda env create -f environment.yml
This installs the necessary libraries and Python 3.8, which enables us to harness Stable Baselines 3. Upon installing all the dependencies, activate the environment using
conda activate sprl
Project received a First Class Honours.