Resource Administrator A.I.
Cesar coded a Deep Q Network: a network that learns how to play a game designed and coded by the student. The A.I. plays through test iterations of the game by trying different strategies. Through this, it determines which strategy is best to use. The goal of this project was to test the limits of the performance of a Deep Q Network when given the task of administering several resources—all in an environment where random events force it to spend some of those resources.