IEEE CoG 2019 - Industry Day - Christoffer Holmgård (modl.ai)
summary
Model AI claims it converts research into deployable tools: it builds Monte Carlo Tree Search agents adapted with learned heuristics to simulate player styles, plus player archetype classification, anomaly detection, personalization and PCG. A 150‑person mobile studio gets a working test harness after an 8‑week integration that runs headless to generate balance stats and replace tedious 1v1 manual playtests. Methods come straight from papers, the system generalizes across similar PvP games, and ongoing maintenance remains part of the engagement.
AI-written summary · about
chapters (12)
- 0:00Introduction
- 1:38The pursuit gap
- 9:07The gap of wasted ideas
- 12:10The triangle pyramid
- 14:48AI personas
- 15:55Player archetypes
- 16:40Game delivery
- 18:08Game design
- 19:13Challenges
- 21:01Benefits
- 21:47Major challenges
- 23:09Roadmap
related talks
38mAI in action: How to use practically in iGaming beyond the hype?
01h 01mIntroduction to Practical AI
52mThe Journey of AI in Games: A Technical and Philosophical overview
18mRe-imagining mobile gaming studios with Gen AI
29mThe Present & Future of AI and Games
01h 18mTotal War: how AI can deliver entertainment.- Duygu Cakmak & Guy Davidson [ACCU 2018]
46mAI Takeover
21mMeet your new and improved teammate! Human-directed AI agents and gaming