Artificial Intelligence & Machine Learning with Unity3D

Name: Artificial Intelligence & Machine Learning with Unity3D
Rating: 3.3 (16 reviews)

Learn how to create a Self-driving Car or an A.I. that learns to play Flappy Bird

Created byARdeveloper TT

Last updated 9/2019

English

English [Auto],

What you'll learn

How a neural-network works
Set-up of the ML-Agents toolkit with Unity3D & Python
Different machine-learning techniques: Reinforcement Learning & Imitation Learning
Several practical examples: A.I. learns to play FlappyBird, Self-driving Car & 3D-Roller Ball Agent
The ML-Agents components

Course content

4 sections • 18 lectures • 1h 6m total length

Intro2:22
Explore machine learning and artificial intelligence in Unity 3D, training neural networks with reinforcement and imitation learning through hands-on projects like 3D roller ball, Flappy Bird, and a self-driving car.
Set up of the ML-Agents Toolkit8:09
Set up the ml-agents toolkit by downloading the project from github, run a basic scene to train agents with reinforcement learning and rewards, and export the trained models.
What is a Neural-Network?3:50
Understand what a neural network is, from inputs and outputs to neurons, layers, weights, bias, and activation function. See how Unity trains these networks using reinforcement and imitation learning.
ML-Agents Key Components2:54
Explore the core ML-Agents components in Unity: learning environment, multiple agents, brains (player, heuristic, learning), and the academy with external communication to train neural networks.

3D - RollerBall Project Overview0:52
Explore a simple 3d rollerball reinforcement learning project in Unity, where an agent ball seeks the shortest path to a target cube, then resets and re-spawns the cube for learning.
RollerBall Set up12:21
Create a Unity rollerball agent in a new scene with a floor, target, and rigidbody, then build academy and brains to collect observations, apply actions, and train via rewards.
Training the AI5:55
Learn to train a neural network for a Unity ML-Agents project, adjust trainer settings, monitor rewards with TensorFlow dashboard, and export the trained model into the scene assets.
Project Files

Flappy Bird Project Overview1:09
Explore a reinforcement learning project that trains a Flappy Bird clone to achieve an unlimited score in Unity3D. Train agents and test a pretty much perfect AI with the toolkit.
Explanation of the basic Scene4:55
Explore a complete Flappy Bird clone in Unity3D, featuring a bird with a rigid body, a pipes spawner with colliders, and a scoring system that increments on passing pipes.
Set Up of the ML Agents Components7:10
Learn how to set up ml agents components in Unity by building a Flappy Bird academy with agents and brains, configuring observations and actions, and preparing training with accelerated time.
Training FlappyBird2:51
Train the agent by creating multiple social environments to speed learning and run the training to maximize reward. Set the train config to 500000 steps to stop after that limit.
Project Files

Self-driving Car Overview0:44
Demonstrate driving behavior through imitation learning to train a self-driving car, using human-provided inputs instead of trial-and-error. Explore reinforcement learning concepts and how human guidance steers the agent.
Explanation of the basic Scene2:18
Import and run a Unity3D self-driving car scene, control the car with keyboard input, use colliders and standard assets, and train the car to complete a full lap.
Set Up of the ML Agents Components6:57
Set up ml agents components in Unity to train a car agent with reinforcement learning, normalizing observations and actions via academy and brains to train neural network.
Training the Car4:15
Train the car by recording demonstrations and creating a training demo file in the demonstrations folder. Configure the offline brain and run imitation learning to produce a trained model.
Project Files

Requirements

A basic understanding of C# and Unity3D is helpful

Description

This crash-course is about machine Learning & Artificial Intelligence with Unity3D.

Why using Unity3D for Artificial Intelligence?

Unity3D is the perfect environment in order to train your own AIs. Let’s take the example of a Self-driving Car. What you need is complex environments where there are a lots of realistic physical interactions. You could provide these datas from interactions with the real world, but this is extreme inefficient and time consuming.

Since games become more and more realistic you can provide these informations from virtual environments. And for that Unity is perfectly positioned.

So, no matter if you are a game developer who wants to create AIs for games or if you are a hobby researcher who just want to play with machine Learning … The ML-Agents toolkit is the perfect start in order to create your own AIs.

What do we learn in this crash-course?

This course is structured into 4 major sections:

Introduction
This section covers everything in order to get a quick start with the ML-Agents Toolkit. You will learn:
-Set up of the ML-Agents toolkit with Tensorflow
-What is a neural-network?
-The Key Components of the Ml-Agents toolkit

3D Roller Ball AI
This lecture will give you a first impression of the Ml-Agents toolkit in practice. You will learn how to set up the environment and all the necessary components in order to train the AI.

A.I. learns to play Flappy Bird
Instead wasting your time with playing this game, we will code our own A.I. that learns to play Flappy Bird by using Reinforcement Learning.
After training the AI is able to achieve an unlimited score in this game.
Self-driving Car
The Self-driving Car is the probably the most famous example for Artificial Intelligence, so we will cover this as well. To train the Car we will use a technique called Imitation Learning.
Imitation Learning is special, because this method uses the inputs from a human Player in order to train the neural network.

Who this course is for:

Anyone who wants to learn artificial intelligence in practice

Artificial Intelligence & Machine Learning with Unity3D

What you'll learn

Explore related topics

Course content

Introduction4 lectures • 17min

3D Roller-Ball A.I - Reinforcement Learning4 lectures • 19min

A.I. learns to play FlappyBird5 lectures • 16min

Self-driving Car - Imitation Learning5 lectures • 14min

Requirements

Description

Who this course is for: