Developing a Machine Learning Model for Playing a Platformer Video Game in Unity and TensorFlow

This thesis deals with game development and the use of artificial intelligence in the domain of video games, especially artificial neural networks. It covers some of the basics of game development in the Unity game engine, as well as some basics of machine learning and artificial intelligence. Basically, it follows the process of developing a platform game using the Unity game engine and applying a deep q learning algorithm, developed using the Python library TensorFlow, to teach the agent how to play said game. The thesis concludes that Unity is an excellent reinforcement learning tool since it provides a secure and modular environment in which agents can learn