Reinforcement Learning: AI Flight with Unity ML-Agents

Reinforcement Learning: AI Flight with Unity ML-Agents

https://www.udemy.com/course/ai-flight/

Teach airplanes to fly with Unity's Reinforcement Learning platform



4.6 (122 ratings)



632 students enrolled



创建者 Adam Kelly Immersive Limit



上次更新 3/2020



英语



英语 [自动生成]

要求



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



说明



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.







此课程面向哪些人：



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