Bayesian Optimization-based Search for Agent Control in Automated Game Testing

TL;DR

This paper presents a novel automated game testing method using agents controlled by Bayesian Optimization to efficiently explore game levels, improve bug detection, and enhance map coverage without scalability issues.

Contribution

It introduces a game-specific Bayesian Optimization model that overcomes traditional scalability problems, enabling efficient and effective automated game level exploration.

Findings

Improved map coverage in less time

Enhanced exploration distribution

Scalable Bayesian Optimization model

Abstract

This work introduces an automated testing approach that employs agents controlling game characters to detect potential bugs within a game level. Harnessing the power of Bayesian Optimization (BO) to execute sample-efficient search, the method determines the next sampling point by analyzing the data collected so far and calculates the data point that will maximize information acquisition. To support the BO process, we introduce a game testing-specific model built on top of a grid map, that features the smoothness and uncertainty estimation required by BO, however and most importantly, it does not suffer the scalability issues that traditional models carry. The experiments demonstrate that the approach significantly improves map coverage capabilities in both time efficiency and exploration distribution.