GDC + [email protected] 2018 Session Scheduler

View, browse and sort the ever-growing list of GDC sessions by time, pass type, track, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App. Sessions do fill up, so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.

In order to best utilize Session Scheduler, please use the login credentials you've set up on this page as your login credentials on our GDC Mobile App. Your login credentials are the same as your registration login. You can download the app on iTunes or Google Play.

Unity for Deep Learning: ML-Agents Explained (Presented by Unity Technologies)

Sponsor Speakers:

Arthur Juliani (Deep Learning, ML-Agents, Unity Technologies)

Mike Geig (Global Head of Evangelism Content, Unity Technologies)

Location: Room 3022, West Hall

Date: Tuesday, March 20

Time: 5:30pm - 6:30pm

Pass Type: All Access, GDC Conference + Summits, GDC Conference, GDC Summits, Expo Plus, Audio Conference + Tutorial, Educators Summit, Indie Games Summit - Get your pass now!

Topic: Programming

Format: Sponsored Dev Day

Vault Recording: Video

Audience Level: All


Unity is building a new generation of tools to empower game developers with techniques from modern machine learning. Presenters will walk through recent developments in Deep Reinforcement Learning, and show how they can be applied to the development and testing of in-game AI using ML-Agents, a new open-source toolkit built to enable training and deploying Deep Learning models within Unity. In addition to walking through the current features of ML-Agents, presenters will also demonstrate new features which enable training agents using only human demonstrations, as well as training many agents within a single scene.


The attendees will learn how to use the latest learning methods (Curriculum learning, imitation learning, etc.) included in the ML-Agents toolkit to train agents with Unity. We will showcase the process through a live demo that uses a real game made with Unity.

Intended Audience

Primarily intended for developers who are interested in using Unity for deep learning, but anyone with Unity development experience can participate.