The era of self-driving cars is almost upon us, at least according to Elon Musk. Hence, it’s probably about time to learn how to make one for ourselves. While this article does not go into such depths, it’s enough to make simulated cars that are proficient on any track.
EDIT: This story has been updated on 1.1.2021 to the match the release (1.0) version of ML-Agents.
Note: This article is for people who already have a basic idea about working with Unity and are interested in Neural Networks and Reinforcement Learning. No prior experience with neural networks and/or PhD required! This article provides all needed to obtain the following result: