Sign In

Communications of the ACM

ACM Careers

Machine Learning Could Create the Perfect Game Bosses

View as: Print Mobile App Share:
red character in videogame maze

The EQS tool can refactor code for a game's characters and environment from a single behavior tree.

Credit: Getty Images

Romain Trachel and Alexandre Peyrot, machine-learning specialists at Eidos-Sherbrooke, demonstrated a game tool at Unreal Fest 2022 that combines machine learning with a feature which lets developers use spatial data to inform AI decisions. 

This is normally handled through behavior trees, but in the demo the AI behavior was driven by a machine-learning model. The Unreal Engine Environment Query System (EQS) acts as the AI's eyes and ears, providing information about its environment, while the machine-learning model becomes its brain and decides how it should respond.

"If a developer decided to activate a stronger chase mode, the only thing to do is to increase a reference value in the EQS tests," Trachel and Peyrot said in an email. "It really has the potential to simplify the development workflow, because in actual game productions, it would be up to a game designer to decide which game variables must be tuned in order to change the difficulty."

From Wired
View Full Article – May Require Paid Registration


No entries found