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

Abstract

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.

Info

GDC Vault: AI-Driven-QA-Simulating-Massively

Slide: Kurabayashi_AI_Driven.pdf

Citation: .bib format