A Metric Learning Approach to Anomaly Detection in Video Games

TL;DR

This paper introduces a deep metric learning approach using Siamese networks for anomaly detection in video games, aiming to automate bug identification during quality assurance.

Contribution

It proposes State-State Siamese Networks (S3N) for effective anomaly detection in video games, demonstrating their ability to identify bugs through empirical evaluation.

Findings

S3N learns meaningful embeddings for video game states

S3N successfully detects various common video game bugs

Empirical results show improved bug detection accuracy

Abstract

With the aim of designing automated tools that assist in the video game quality assurance process, we frame the problem of identifying bugs in video games as an anomaly detection (AD) problem. We develop State-State Siamese Networks (S3N) as an efficient deep metric learning approach to AD in this context and explore how it may be used as part of an automated testing tool. Finally, we show by empirical evaluation on a series of Atari games, that S3N is able to learn a meaningful embedding, and consequently is able to identify various common types of video game bugs.