A Beginners Guide To Machine Learning with Unity

A Beginners Guide To Machine Learning with Unity

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.

Requirements

You should be familiar with the Unity Game Engine.
You should have a working knowledge of C#.
You should have a healthy appreciation for mathematics and statistics.

Description

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 algorithmsneural networkshuman player captured training setsreinforcement learningUnity’s ML-Agent pluginTensorflowContents and OverviewThe 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.

Overview

Section 1: Introduction

Lecture 1 Introduction

Lecture 2 What is Learning?

Lecture 3 How to Study This Course

Lecture 4 FAQs

Lecture 5 Machine Learning 101

Section 2: Genetic Algorithms

Lecture 6 DNA Inspired Data Structures

Lecture 7 Camouflage Training with Genetic Algorithms Part 1

Lecture 8 Camouflage Training with Genetic Algorithms Part 2

Lecture 9 Camouflage Challenge

Lecture 10 Coding Movement with Genes Part 1

Lecture 11 Coding Movement with Genes Part 2

Lecture 12 Distance Challenge

Lecture 13 Note: Unity Versions Might Mess Up Package Imports

Lecture 14 Moving GAs with Senses Part 1

Lecture 15 Moving GAs with Senses Part 2

Lecture 16 Moving GAs with Senses Part 3

Lecture 17 Maze Walking Challenge

Lecture 18 Maze Walking Challenge Solution Part 2

Lecture 19 Not So Flappy Birds Part 1

Lecture 20 Not So Flappy Birds Part 2

Lecture 21 Extra Readings

Section 3: Perceptrons: The making of a Neural Network

Lecture 22 The Perceptron

Lecture 23 Challenge

Lecture 24 Programming and Training a Perceptron

Lecture 25 Exercise 1

Lecture 26 Exercise 2

Lecture 27 Perceptron Classification

Lecture 28 Perceptron Learning from Experience

Lecture 29 Saving & Loading Perceptron Values

Section 4: Artificial Neural Networks

Lecture 30 Introduction to Neural Networks

Lecture 31 Programming An Artificial Neural Network Part 1

Lecture 32 Programming An Artificial Neural Network Part 2

Lecture 33 Programming An Artificial Neural Network Part 3

Lecture 34 ANN FAQs

Lecture 35 Working with Activation Functions

Lecture 36 Challenge

Lecture 37 Extra Readings

Section 5: Neural Networks in Practice

Lecture 38 Developing a Neural Network that Plays Pong Part 1

Lecture 39 Developing a Neural Network that Plays Pong Part 2

Lecture 40 Developing a Neural Network that Plays Pong Part 3

Lecture 41 Challenge

Lecture 42 Gathering Training Data from the Player Part 1

Lecture 43 Gathering Training Data from the Player Part 2

Lecture 44 Training with Player Data Part 1

Lecture 45 A Note to the Astute

Lecture 46 Training with Player Data Part 2

Lecture 47 Training with Player Data Part 3

Section 6: Reinforcement Learning with the Q-Network

Lecture 48 Reinforcement Learning and Q-Networks

Lecture 49 Training a Neural Network with Q-Learning Part 1

Lecture 50 Training a Neural Network with Q-Learning Part 2

Lecture 51 Training a Neural Network with Q-Learning Part 3

Lecture 52 Challenge

Lecture 53 Extra Readings

Section 7: ML-Agents

Lecture 54 Read This First

Section 8: Unity’s ML-Agents V0.3 [DEPRECATED]

Lecture 55 Setup

Lecture 56 Training Your First ML-Agent V0.3

Lecture 57 Migrating from V0.2 to V0.3

Lecture 58 ML-Agent’s FAQ

Lecture 59 Creating an ML-Agent From Scratch Part 1

Lecture 60 Creating an ML-Agent From Scratch Part 2

Lecture 61 ML-Agents Cheat Sheet

Lecture 62 An Avoiding ML-Agent Part 1

Lecture 63 An Avoiding ML-Agent Part 2

Lecture 64 Challenge

Lecture 65 Top 10 Tips for Neural Network Best Practice

Lecture 66 Environment Sensing ML-Agent

Lecture 67 Goal Seeking Wall Jumping Part 1

Lecture 68 Goal Seeking Wall Jumping Part 2

Lecture 69 Extra Readings

Section 9: Unity’s M-Agents V0.2 [DEPRECIATED]

Lecture 70 About This Section

Lecture 71 Setting up TensorFlow – Starter Files

Lecture 72 Setting up TensorFlow – Windows

Lecture 73 Setting up TensorFlow – Mac

Lecture 74 An Overview of ML-Agents

Section 10: A Final Word

Lecture 75 Thank you

Lecture 76 Where to Now?

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.

Course Information:

Udemy | English | 13h 3m | 9.60 GB
Created by: Penny de Byl

You Can See More Courses in the Developer >> Greetings from CourseDown.com