Reinforcement Learning: AI Flight with Unity ML-Agents
Teach airplanes to fly with Unity's Reinforcement Learning platform
4.6 (122 ratings)
632 students enrolled
创建者 Adam Kelly Immersive Limit
Intermediate programming skills (Unity uses C#)
A computer that can run Unity 2019.2 or above
Basic Unity skills (how to navigate and use the interface)
Optional: Basic Blender skills (how to navigate and use the interface)
Optional: Prior Machine Learning experience - It will help with understanding, but isn't necessary
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 recorded with ML-Agents version 0.11, there is a lecture devoted to the few changes needed to use the latest versions (v0.12 and v0.13).
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.
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
DevOps Project CICD with Jenkins Ansible Docker Kubernetes
Groartig Singen - die Lehre von TVS-the Vocalist Studio
Blender Character Creator v2.0 for Video Games Design
Linux Heap Exploitation - Part 1
URBANYX Powerpoint+Keynote+Google Slide
FilmEditingPro - The Art of Trailer Editing (Pro Version 专业版)
VitaliStore - All Design Bundle Papercraft Sculptures Design 动物纸模模型 纸模型雕塑设计
SceneCity Pro 1.5.0 for Blender 2.8 快速创建城市建筑Blender插件
Plastic Wrap Torn Paper Bundle 4068119
UE4 室内公共空间模型 UE4 室内设计模型 办公室模型CGTrader UE4 Office Low-poly
Spectrum Grades - ULTRA-FILMGRAIN 4K PROFESSIONAL ORGANIC ANALOGUE FILM LOOK 8MM
30GB Hum3D各种车辆模型 30gb of hum3d vehicles cars/trucks/bikes/etc