This repository is a simple example of how to train an agent using Q-Learning to play a video game. One of the coolest aspects of this method is that the agent learns how to play the game through self exploration instead of human-labeled data. A major drawback of supervised learning based on human curated data is that the model can, at best, learn how to do a job as well as the humans who curated the data. Humans do a near perfect job solving some problems, but most of the time we are not perfect. By training the agent through its own self play, it can actually become better than humans and devise strategies that have never been used before. This is how AlphaGo is able to play Go at a super-human skill level.
If you'd like to collaborate on a project, learn more about me, or just say hi, feel free to contact me using any of the social channels listed below.