This repository contains the code for Deakin SIT215 Investigating Reinforcement Learning Project by Ethan G. Keirs(220250887).

Task requirement 2 “Read and complete the following tutorial: https:/www.learndatasci.com/tutorials/reinforcement-q- learning-scratch-python-openai-gym/, ensuring that you can reproduce all steps discussed” can be found as the Taxi.ipynb file. This should be run through jupternotebook

Task requirement 4 “Complete the following tutorial to explore the Cart-Pole environment in the Gym: http://kvfrans.com/simple-algoritms-for-solving-cartpole/.” Can be found in the crat-pole-code folder which contains a random policy file, a Q-learning file and a policy gradient method file. This should be run through terminal

The environments used are
1. Taxi-v3  (https://gym.openai.com/envs/Taxi-v3/)
2. Cartpole-v1 (https://gym.openai.com/envs/CartPole-v1/)
3. FrozenLake-v0  (https://gym.openai.com/envs/FrozenLake-v0/)


The graphs were made using the master.py file, for this code to work you need the src folder downloaded, it should  be run in terminal. In the python file at the bottom is were the functions are invoked. Only one can be run at a time and the others commented out. Choose which agent and environment you want to run, and uncomment that line. I do #Not Claim# ownership of the code in the src folder, it is not mine, you will find the code appropriately referenced in the report and on the .py files. The code was used to merely show graphs of how the enviroments work.