In this recording of the live session, you'll learn how to create a machine learning experience that has a basic input (one or two dimensional vector observation), an obvious reward, and simple reset state. Throughout the session, learners will be able to:
Define Machine Learning
Discuss how ML differs from and works with Artificial Intelligence
Identify observations for an ML agent to make in a given Scene
Identify ways to reward the ML agent that will reinforce desired behavior
Script the ML Agent to collect observations about conditions in the scene and calculate rewards accordingly
Script the ML Agent to change behavior based on rewards received
 

Materials

MLAgentsLiveSessionAssets.zip

MachineLearning_LiveSession_TrainTheAgent.JPG

Select your Unity version

Last updated: October 21, 2020

2019.4

Language

English

Also included in

CourseML-Agents: Hummingbirds

Submission Gallery

Good walkthrough

Nice tutoriallll

Fun and a lot of new knowledge

Thanks for this great course, wish there would be more!

Had fun creating and learning about ML-agents !!

Always wanted to learn ML and combine it with game dev. Even, not completely trained AI beat me though, creator being beaten by creation. :(

Seems, that AI is really good hummingbird

This course was very interesting for me

The ML Agent beat me this time, but I beat it in the next trial (I didn't screenshot it that time though :/)

Very happy with the outcome of what Immersive Limit was able to deliver on a project for free. Great tutorial!

hummingbird

I was only able to train her to 28-30 rewards

Happy to see everything working

Really enjoyed following along with this tutorial, planning on adapting it to use for some educational research. Some of the ml-agents material was out of date but I was able to get everything working with the current version with a few changes.

ML Humming Bird

This tweaking made the bird more faster and non stuck

Live Session - Getting Started with Machine Learning in Unity