Dynamic Scheduling of NPC Behaviours in Modern Video Games

Persistent Non Player Characters (NPCs) in many modern video games follow schedules guiding their routines and behaviors over time as the player engages in play inside the game’s virtual world. In a game like Ubisoft’s recently released Watchdogs: Legion, where schedules are a player-facing game mechanic, a robust scheduling system is highly important and critical to the game’s financial and critical success.
Making good schedules for NPCs in this context, however, is surprisingly complex. To address challenges in this space, we will leverage artificial intelligence and machine learning to build a system capable of generating “good” schedules. In this context, schedules are deemed “good” if they pass designer defined heuristics and measures of fitness. Using feedback and reinforcement, the system will be extensively trained to iteratively generate better and better schedules until it can consistently pass the “goodness” test, at which point it is ready for deployment and production use.

Faculty Supervisor:

Michael Katchabaw

Student:

Jonathan Tan

Partner:

Ubisoft

Discipline:

Computer science

Sector:

Information and cultural industries

University:

Western University