This is a project I presented as my final project at CSU Long Beach for the CECS 406 Introduction to Machine Learning class. The syllabus of the class was essentially Supervised and Semi-Supervised learning; but I chose to make my final project around unsupervised learning (Reinforced Learning). This was supposed to use Deep Reinforced Learning and Genetic Algorithm (Weird combination, I know, that was my favorite topics at the time and it seemed a good fit), but I later found a research paper about Deep Q-learning by Google Deepmind (link to publication).
I included the paper I submitted for this project. Bear in mind that those are old and I won't edit them for spelling mistakes. I'll publish new documents in the future if make some progress.