Final Submission of all code relating to the RL Assignment 2023 Hons
To train each model, there is a code/train_DQN and a code/train_PPO. At the top of each of these files the hyper paramaters can be changed. That is also where you specify the environment you want to use, and that has to be an environment in environments.py so that the action space and rewards work correctly
An env.yaml is provided to avioid dependecy issues.