Search and Compare course prices, ratings, and reviews. Over +350 Design and Technology courses in one place!

A Beginner’s Guide To Machine Learning with Unity Tutorial

(12 customer reviews)
Product is rated as #121 in category Development

What you’ll learn

  • Build a genetic algorithm from scratch in C#.
  • Build a neural network from scratch in C#.
  • Setup and explore the Unity ML-Agents plugin.
  • Setup and use Tensorflow to train game characters.
  • Apply newfound knowledge of machine learning to integrate contemporary research ideas in the field into their own projects.
  • Distill the mathematics and statistic behind machine learning to working program code.
  • Use a Proximal Policy Optimisation to train a neural network.

What if you could build a character that could learn while it played?  Think about the types of gameplay you could develop where the enemies started to outsmart the player. This is what machine learning in games is all about. In this course, we will discover the fascinating world of artificial intelligence beyond the simple stuff and examine the increasingly popular domain of machines that learn to think for themselves.

In this course, Penny introduces the popular machine learning techniques of genetic algorithms and neural networks using her internationally acclaimed teaching style and knowledge from a Ph.D in game character AI and over 25 years experience working with games and computer graphics.  In addition she’s written two award winning books on games AI and two others best sellers on Unity game development. Throughout the course you will follow along with hands-on workshops designed to teach you about the fundamental machine learning techniques, distilling the mathematics in a way that the topic becomes accessible to the most noob of novices.

Learn how to program and work with:

  • genetic algorithms
  • neural networks
  • human player captured training sets
  • reinforcement learning
  • Unity’s ML-Agent plugin
  • Tensorflow

Contents and Overview

The course starts with a thorough examination of genetic algorithms that will ease you into one of the simplest machine learning techniques that is capable of extraordinary learning. You’ll develop an agent that learns to camouflage, a Flappy Bird inspired application in which the birds learn to make it through a maze and environment-sensing bots that learn to stay on a platform.

Following this, you’ll dive right into creating your very own neural network in C# from scratch.  With this basic neural network, you will find out how to train behaviour, capture and use human player data to train an agent and teach a bot to drive.  In the same section you’ll have the Q-learning algorithm explained, before integrating it into your own applications.

By this stage, you’ll feel confident with the terminology and techniques used throughout the deep learning community and be ready to tackle Unity’s experimental ML-Agents. Together with Tensorflow, you’ll be throwing agents in the deep-end and reinforcing their knowledge to stay alive in a variety of game environment scenarios.

By the end of the course, you’ll have a well-equipped toolset of basic and solid machine learning algorithms and applications, that will see you able to decipher the latest research publications and integrate the latest developments into your work, while keeping abreast of Unity’s ML-Agents as they evolve from experimental to production release.

What students are saying about this course:

  • Absolutely the best beginner to Advanced course for Neural Networks/ Machine Learning if you are a game developer that uses C# and Unity. BAR NONE x Infinity.
  • A perfect course with great math examples and demonstration of the TensorFlow power inside Unity. After this course, you will get the strong basic background in the Machine Learning.
  • The instructor is very engaging and knowledgeable. I started learning from the first lesson and it never stopped. If you are interested in Machine Learning , take this course.

Who this course is for:

  • Anyone wanting to learn about the potential of machine learning in games.
  • Anyone wanting a deeper understanding of the algorithms and theories underlying Unity’s ML-Agents.
  • Anyone wanting to know how to setup and work with ML-Agents.

12 reviews for A Beginner’s Guide To Machine Learning with Unity Tutorial

4.3 out of 5
Write a review
Show all Most Helpful Highest Rating Lowest Rating
  1. David Pulcifer

    There is a lot of great material in this course, and I am really excited to apply this to future projects!

    I love that this course dives right in and gets you building Neural Networks without spending ages on theory and mathematics before you start making anything. Honestly, the math was much easier to learn when applying it in code, and the concepts solidified much faster than my previous attempts to learn ANNs other places.

    The main thing that I think needs improvement is the variable naming conventions make the code really hard to understand in the Neural Network sections. I’m really not a stickler for that sort of thing if it doesn’t detract from learning, but in this case, the code is how the instructor is teaching the main concept, so in this case it would be much easier to grasp if the variable naming was more explanatory.

    Helpful(0) Unhelpful(0)You have already voted this
  2. Michael Leveille

    I started taking this course almost 2 years ago but could not give it the time it deserved. I recently started over and with proper time for it am delighted that what I did do 2 years ago is quickly coming back. Penny is one of the best instructors for Unity and game development concepts at UDEMY. I have almost all her courses.

    Helpful(0) Unhelpful(0)You have already voted this
  3. Thomas Schwan

    A good introduction to the concepts of Machine Learning. However as Unity is updating its ML-Agents constantly the examples provided will not run with the latest version.

    Helpful(0) Unhelpful(0)You have already voted this
  4. Daniel Silva

    This course delivers with the same quality that I have come to expect from all of Penny’s courses. The concepts were, surprisingly, simple enough to understand, but I will personally need to spend a lot more time on the subject before I am confident in creating my own agents.

    Helpful(0) Unhelpful(0)You have already voted this
  5. Jonas van Kerckhove

    it was very clear and simple to follow, even managed to get the ML-agentsd excersises to work

    Helpful(0) Unhelpful(0)You have already voted this
  6. Gilles Walther

    Always great hearing a passionate speaker about their job. Second course I take with the teacher and I’m sure it’s gonna be as good if not better.

    Helpful(0) Unhelpful(0)You have already voted this
  7. Curtis Crum

    I could not see a lot of the material on the slides from the conference. I am so glad the whole course is not that way. Its nice to know this was presented at a conference, but a link would be sufficient, especially in the beginning.

    Helpful(0) Unhelpful(0)You have already voted this
  8. Leonardo Tasca

    That’s a good course, unfortunately the part abut mlagents isn’t updated.

    Helpful(0) Unhelpful(0)You have already voted this
  9. Sarah Rawlinson

    I’ve been looking for the right entry point for learning ML for a long time but I was always overloaded by the equations, this course started off in just the right place. I’ve had a load of fun with genetic algorithms and it was a lot simpler than I expected. I look forward to finishing the course and hopefully understanding neural networks to the point I can use them in my unity games.

    Helpful(0) Unhelpful(0)You have already voted this
  10. James Surine

    I was able to create an AI in Unity3D that plays asteroids reasonably well using ML-Agents and information in this course. Would be nice if the ML-Agents example code in the course could be kept up to date with the current release occasionally even if the videos are not but I was able to figure things out regardless. You can check out my results here Overall it was an interesting experience to learn about machine learning and what goes on under the hood a little bit in more sophisticated systems like recent advancements in self driving cars and things seen on the two-minute papers youtube channel. Machine Learning ends up being a little more involved that just setting up the simulation and letting it run but that’s probably why this is still a somewhat new field of technology.

    Helpful(0) Unhelpful(0)You have already voted this
  11. Rihards Gailis

    Didn’t expect the first lesson to be a video of a lecture. The quality of the video was a bit disappointing, but the content was good. So I am excited for what’s to come.

    Helpful(0) Unhelpful(0)You have already voted this
  12. Veera Narayana Kandepu

    Its good content

    Helpful(0) Unhelpful(0)You have already voted this

    Add a review

    Your email address will not be published.

    A Beginner’s Guide To Machine Learning with Unity Tutorial
    A Beginner’s Guide To Machine Learning with Unity Tutorial


    Compare items
    • Total (0)
    Shopping cart