GDC + [email protected] 2018 Session Scheduler

View, browse and sort the ever-growing list of GDC sessions by time, pass type, track, and format. With GDC Session Scheduler, you can build your schedule in advance and access it during the show via export or with the GDC Mobile App. Sessions do fill up, so please arrive early to sessions that you would like to attend. Adding a session to your schedule does not guarantee you a seat.

In order to best utilize Session Scheduler, please use the login credentials you've set up on this page as your login credentials on our GDC Mobile App. Your login credentials are the same as your registration login. You can download the app on iTunes or Google Play.

AI-Driven QA: Simulating Massively Multiplayer Behavior for Debugging Games


Shuichi Kurabayashi (Technical Advisor/Director of Cygames Research, Cygames, Inc.)

Location: Room 20, North Hall

Date: Wednesday, March 21

Time: 9:30am - 10:30am

Pass Type: All Access, GDC Conference + Summits, GDC Conference - Get your pass now!

Topic: Programming

Format: Session

Vault Recording: Video

Audience Level: Intermediate

At Cygames, one of the largest mobile game developers in Japan, the team provides a strategic multiplayer digital card game for millions of unique users. The Cygames team faces serious costs when debugging enormous amounts of cards and card combinations, which are continuously released because each card has unique functions and visual effects. That's why they developed a novel AI-driven automatic quality assurance (QA) toolkit that learns massively multiplayer behaviors from gaming logs to simulate various play styles and decision-making tendencies. In this session, Cygames will explain a detailed process for developing an AI-driven QA framework, including a method to extract a frequent itemset of cards and actions from a noisy gaming log, and a method to convert the frequent itemset to parameters for controlling an AI-bot. The speaker wil explain how to implement your own AI-driven QA toolkit exploiting your gaming logs in a step-by-step manner, and how it improves the efficiency of your QA process.


Attendees will get an insight into the principles and considerations of why, when, and how they can develop AI-driven automatic QA toolkit tailored to their own title. The speaker will explain how to utilize the existing well-designed machine learning toolkits such as Deeplearning4j and Google's TensorFlow. Sample codes are provided.

Intended Audience

This talk is primarily aimed at engineers who are tackling bugs and unintended behavior of gaming systems. Although a minimal programming skill is required, anyone with an interest in AI and QA is welcome. It will also satisfy data scientists who are analyzing gaming logs for any purpose.