You've been logged out of GDC Vault since the maximum users allowed for this account has been reached. To access Members Only content on GDC Vault, please log out of GDC Vault from the computer which last accessed this account.

Click here to find out about GDC Vault Membership options for more users.


The Number One Educational Resource for the Game Industry

Session Name: Machine Learning Summit: Walk Lizzie, Walk! Emergent Physics-Based Animation through Reinforcement Learning
Speaker(s): Jorge del Val Santos
Company Name(s): Embark Studios
Track / Format: Machine Learning Summit

Did you know free users get access to 30% of content from the last 2 years?

Get your team full access to the most up to date GDC content

Overview: Can you animate a user-created creature in a completely physics-based, interactive fashion? How about a hundred? In this talk the speaker will present a new reinforcement learning approach to automatic animation. With the click of a button and no animators involved, the speaker will show how to give life to digital creations by allowing them to learn by themselves. Under this paradigm, animation is no longer a starting point, but an emergent property of the anatomy: the problem of locomotion becomes more akin to robotics than to classical animation. Join this journey through the problems, methods, and results towards our vision: empowering anyone to create.

Game Developers Conference 2022

Jorge del Val Santos

Embark Studios

free content

Machine Learning Summit