Whether you’re an expert in Machine Learning or just interested in how it can be applied to games, this challenge is a great opportunity for you to learn, explore, inspire and get inspired.
We want to see how you apply the new Curriculum Learning method. But we’re not looking for any particular genre or style, so get creative! We’ll send some gifts and surprises to the creators who get the most likes and votes at the end of the challenge.
How to enter
The first round of The Machine Learning Agents Challenge is from Dec 7, 2017 to Jan 31, 2018, and it is open to any developer with basic Unity knowledge and experience. Here’s how to participate:
Log in to Unity Connect using your Unity ID.
Train your project with ML-Agents and upload to Connect with “ML-Agents” tag.
Add a Github repo link of your training environment in the submission.
Post a link to your showcase in the Unity Machine Learning discussion channel.
What is the Unity Machine Learning Agents feature?
Unity Machine Learning Agents offers a flexible way to tackle development challenges quickly and efficiently by using intelligent agents across a new generation of robotics, games, and beyond.
It makes it possible to train agents using reinforcement learning or evolutionary methods. This is done via a C# framework of Reinforcement Learning (RL) abstractions and a Python binding for external ML system integration.
More information on Unity Machine Learning Agents
Using Machine Learning Agents in a real game: a beginner’s guide
Introducing ML-Agents v0.2: Curriculum Learning, new environments, and more
Introducing: Unity Machine Learning Agents
Unity Machine Learning home page
Download the latest release on the ML GitHub page.
If you have any questions about using ML-Agents or this Challenge, please feel free to reach us at email@example.com or visit our website at unity3d.ai.