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.

close

The Number One Educational Resource for the Game Industry

Session Name: Reinforcement Learning Based Character Locomotion in Hitman: Absolution
Speaker(s): Michael Buttner
Company Name(s): IO Interactive / Square Enix
Track / Format: Programming

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: Character locomotion systems usually consist of manually crafted blend-trees and large chunks of gameplay code in order to drive and micro-manage them. In this session, we'll talk about the novel approach that we took to create the crowd characters in Hitman: Absolution. This talk will cover how we arranged animation clips in an appropriate data-structure, the controller strategies we used to derive the animation clip selection from high-level AI goals, and how the system can be used in path following scenarios. We will touch on the challenges that we faced during the development of the system.

GDC 2013

Michael Buttner

IO Interactive / Square Enix

free content

Programming

Programming