Reinforcement Learning: AI Flight with Unity ML-Agents

Reinforcement Learning: AI Flight with Unity ML-Agents, available at $49.99, has an average rating of 3.6, with 119 lectures, 1 quizzes, based on 241 reviews, and has 1038 subscribers.

You will learn about Learn how to install, run, and train neural networks with Unity ML-Agents Train airplane agents to fly with Reinforcement Learning, specifically PPO Create a full, playable airplane racing game in Unity with incredibly challenging AI opponents Integrate trained neural networks in a game that can be built and deployed cross-platform Utilize Machine Learning at a high level (no need to write training algorithms) Lots of opportunities to customize the project and make it your own This course is ideal for individuals who are Intermediate software developers with an interest in AI in the Unity3d Game Engine or Developers that want to use Reinforcement Learning, but don't need to know the low level details or Game developers interested in adding neural network AI to their games It is particularly useful for Intermediate software developers with an interest in AI in the Unity3d Game Engine or Developers that want to use Reinforcement Learning, but don't need to know the low level details or Game developers interested in adding neural network AI to their games.

Enroll now: Reinforcement Learning: AI Flight with Unity ML-Agents

Summary

Title: Reinforcement Learning: AI Flight with Unity ML-Agents

Price: $49.99

Average Rating: 3.6

Number of Lectures: 119

Number of Quizzes: 1

Number of Published Lectures: 119

Number of Published Quizzes: 1

Number of Curriculum Items: 120

Number of Published Curriculum Objects: 120

Original Price: $49.99

Quality Status: approved

Status: Live

What You Will Learn

Learn how to install, run, and train neural networks with Unity ML-Agents
Train airplane agents to fly with Reinforcement Learning, specifically PPO
Create a full, playable airplane racing game in Unity with incredibly challenging AI opponents
Integrate trained neural networks in a game that can be built and deployed cross-platform
Utilize Machine Learning at a high level (no need to write training algorithms)
Lots of opportunities to customize the project and make it your own

Who Should Attend

Intermediate software developers with an interest in AI in the Unity3d Game Engine
Developers that want to use Reinforcement Learning, but don't need to know the low level details
Game developers interested in adding neural network AI to their games

Target Audiences

Intermediate software developers with an interest in AI in the Unity3d Game Engine
Developers that want to use Reinforcement Learning, but don't need to know the low level details
Game developers interested in adding neural network AI to their games

Interested in the intersection of video games and artificial intelligence? If so, you will love Unity ML-Agents.

Reinforcement Learning with ML-Agents is naturally more intuitive than other machine learning approaches because you can watch your neural network learn in a real-time 3d environment based on rewards for good behavior. It’s more fun because you can easily apply it to your own video game ideas rather than working with simplified example problems in a library like OpenAI Gym.

In this course, we will create a complete game with incredibly challenging AI opponents.

We’ll start with an introduction to ML-Agents, including how to use and train the example content.
Then, we’ll use Blender to make custom assets for our game (you can skip that part if you just want to code).
Next, we’ll create a full environment for the airplane agents and train them to fly through checkpoints without crashing into obstacles.
Finally, we’ll take our trained agents and build a full game around them that you can play, including menus for level and difficulty selection.

Important note 1: We DO NOT cover the foundations of deep learning or reinforcement learning in this course. We will focus on how to use ML-Agents, which abstracts the hard stuff and allows us to focus on building our training environment and crafting rewards.

Important note 2:While the course was originally recorded with ML-Agents version 0.11, we have updated it for version 1.0.

As you work through the course, you’ll have plenty of opportunities to customize it and make it your own. At the end, you’ll have a complete game that you can share with friends, add to your portfolio, or sell on a game marketplace.

Course Curriculum

Chapter 1: COURSE UPDATES

Lecture 1: ❗❗❗COURSE UPDATE – Unity ML-Agents v1.0

Lecture 2: A Note on Newer Versions

Lecture 3: 1080p Videos

Chapter 2: [v1.0] Unity ML-Agents – Introduction & Setup

Lecture 1: Unity Hub & Anaconda

Lecture 2: New Project, Install ML-Agents, & Import Examples

Lecture 3: 3D Ball Example

Lecture 4: Training 3D Ball Example

Chapter 3: [v1.0 & v0.11] Asset Creation in Blender

Lecture 1: Introduction

Lecture 2: Important Resources & Assets

Lecture 3: Low-Poly Terrain: Setup

Lecture 4: Low-Poly Terrain: Subdivide, Triangulate, & Sculpt

Lecture 5: Low-Poly Terrain: Sculpt the Racetrack

Lecture 6: Low-Poly Rocks: Medium Rock

Lecture 7: Low-Poly Rocks: Tall & Flat Rocks

Lecture 8: Low-Poly Rocks: Colliders

Lecture 9: Low-Poly Rocks: Export

Lecture 10: Checkpoint: First Piece

Lecture 11: Checkpoint: More Pieces, Collider, & Export

Lecture 12: Finish Line Checkpoint

Lecture 13: Low-Poly Airplane: Reference Images

Lecture 14: Low-Poly Airplane: Body (Part 1)

Lecture 15: Low-Poly Airplane: Body (Part 2)

Lecture 16: Low-Poly Airplane: Body (Part 3)

Lecture 17: Low-Poly Airplane: Wings

Lecture 18: Low-Poly Airplane: Horizontal Stabilizer

Lecture 19: Low-Poly Airplane: Landing Gear

Lecture 20: Low-Poly Airplane: Propeller

Lecture 21: Low-Poly Airplane: Export

Chapter 4: [v1.0] Project Setup & ML-Agents Installation

Lecture 1: ML-Agents v1.0 Note

Lecture 2: Important Resources & Assets

Lecture 3: New Project

Lecture 4: Project Clean-up & Install ML-Agents

Chapter 5: [v1.0 & v0.11] Desert Race Path Creation

Lecture 1: Import 3D Meshes

Lecture 2: Desert Terrain & Rock Prefabs

Lecture 3: [v0.11] Airplane Prefab

Lecture 4: [v1.0] Airplane Prefab

Lecture 5: Checkpoint Prefabs

Lecture 6: Desert Area Prefab

Lecture 7: Placing Rocks in the Desert Environment

Lecture 8: Complete Rock Placement

Lecture 9: Race Path

Lecture 10: Complete Race Path

Lecture 11: Boundaries

Chapter 6: [v1.0] Aircraft Area

Lecture 1: Variables

Lecture 2: Awake() & Start()

Lecture 3: ResetAgentPosition()

Lecture 4: Race Condition Fix

Lecture 5: AircraftArea Prefab Setup

Lecture 6: Rotate.cs

Chapter 7: [v1.0] Aircraft Agent & Aircraft Player

Lecture 1: AircraftAgent.cs: Variables

Lecture 2: AircraftAgent.cs: Initialize()

Lecture 3: AircraftAgent.cs: OnActionReceived()

Lecture 4: AircraftAgent.cs: ProcessMovement()

Lecture 5: AircraftPlayer.cs: Input System & Variables

Lecture 6: AircraftPlayer.cs: Heuristic()

Lecture 7: AircraftPlayer.cs: Airplane Prefab Setup

Lecture 8: AircraftPlayer: Input Bindings

Lecture 9: AircraftPlayer.cs: Follow Camera, DecisionRequester, & Test Flight

Lecture 10: AircraftAgent.cs: More Variables

Lecture 11: AircraftAgent.cs: Training Logic in Initialize() & OnActionReceived()

Lecture 12: AircraftAgent.cs: VectorToNextCheckpoint()

Lecture 13: AircraftAgent.cs: GotCheckpoint()

Lecture 14: AircraftAgent.cs: OnEpisodeBegin()

Lecture 15: AircraftAgent.cs: Freeze() & Thaw()

Lecture 16: AircraftAgent.cs: OnTriggerEnter()

Lecture 17: AircraftAgent.cs: OnCollisionEnter & ExplosionReset()

Lecture 18: AircraftAgent.cs: CollectObservations() & Heuristic()

Lecture 19: AircraftAgent: RayPerceptionSensor3D & AircraftAgent Components

Lecture 20: AircraftAgent: Behavior Parameters, AircraftAgent, & Explosion

Chapter 8: [v1.0] Training the Aircraft Agents

Lecture 1: New Training Scene

Lecture 2: Config Files

Lecture 3: Start Training

Lecture 4: Tensorboard & Training Progress

Lecture 5: Training Results

Lecture 6: Introducing Randomness

Lecture 7: Race Your ML-Agents

Chapter 9: [v1.0 & v0.11] Game Logic & Menus

Lecture 1: Introduction

Lecture 2: GameManager.cs: Enums & StateChangeHandler

Lecture 3: GameManager.cs: Accessors & Singleton Logic

Lecture 4: GameManager.cs: Level Loading Logic

Lecture 5: Main Menu Scene + Layout

Lecture 6: Main Menu Content

Lecture 7: MainMenuController.cs: Variables & Dropdown Lists

Lecture 8: MainMenuController.cs: Interaction Logic

Lecture 9: MainMenuController.cs: Hook Up UI, Build Manager, & Game Manager

Lecture 10: Create RaceManager & Other UI Scripts

Lecture 11: RaceManager.cs: Variables & Hook Ups

Lecture 12: RaceManager.cs: More Variables & Accessors

Lecture 13: RaceManager.cs: Awake() & Start()

Lecture 14: RaceManager.cs: Start() Continued

Lecture 15: RaceManager.cs: OnStateChange()

Instructors

Adam Kelly Immersive Limit
3D DEVELOPMENT + DEEP LEARNING

Rating Distribution

1 stars: 3 votes
2 stars: 3 votes
3 stars: 20 votes
4 stars: 62 votes
5 stars: 153 votes

Frequently Asked Questions

How long do I have access to the course materials?

You can view and review the lecture materials indefinitely, like an on-demand channel.

Can I take my courses with me wherever I go?

Definitely! If you have an internet connection, courses on Udemy are available on any device at any time. If you don’t have an internet connection, some instructors also let their students download course lectures. That’s up to the instructor though, so make sure you get on their good side!

Menu