Udemy

Self-driving go-kart with Unity-ML

Name: Self-driving go-kart with Unity-ML
Availability: InStock
Rating: 4.5 (275 reviews)

4.5(275)13k studentsBEGINNEREnglish

Korshub's take

Three Ways to Teach a Go-Kart to Drive Itself

This course uses a simulated go-kart racing around a track as a hands-on way to explore machine learning and reinforcement learning concepts inside Unity. Rather than treating control as one technique, it compares three distinct approaches: a classic PID controller, a neural network trained through imitation (supervised) learning, and a neural network trained through deep reinforcement learning.

Each method is introduced conceptually first, then applied practically, so you can see the trade-offs directly — and in every case, the go-kart completes a lap without crashing. The Unity project and files for all three solutions are provided as a base to extend and improve on.

Note: the instructor flags that the Unity ML-Agents library has moved on considerably since this course was made, so some implementation details are dated even though the core concepts and theory still hold.

About this course

WARNING: take this class as a gentle introduction to machine learning, with particular focus on machine vision and reinforcement learning. The Unity project provided in this course is now obsolete because the Unity ML agents library is still in its beta version and the interface keeps changing all the time! Some of the implementation details you will find in this course will look different if you are using the latest release, but the key concepts and the background theory are still valid. Please refer to the official migrating documentation on the ml-agents github for the latest updates.

Learn how to combine the beauty of Unity with the power of Tensorflow to solve physical problems in a simulated environment with state-of-the-art machine learning techniques.

We study the problem of a go-kart racing around a simple track and try three different approaches to control it: a simple PID controller; a neural network trained via imitation (supervised) learning; and a neural network trained via deep reinforcement learning.

Each technique has its strengths and weaknesses, which we first show in a theoretical way at simple conceptual level, and then apply in a practical way. In all three cases the go-kart will be able to complete a lap without crashing.