Augmenting Automated Game Testing with Deep Reinforcement Learning

TL;DR

This paper presents a DRL-based framework that enhances automated game testing by increasing coverage, discovering exploits, and identifying bugs across various game types, reducing reliance on human testers.

Contribution

The paper introduces a novel DRL-driven approach for automated game testing that adapts and learns to explore game mechanics more effectively than traditional methods.

Findings

DRL improves test coverage in diverse game genres

The approach successfully identifies exploits and bugs

It can evaluate map difficulty and detect common testing issues

Abstract

General game testing relies on the use of human play testers, play test scripting, and prior knowledge of areas of interest to produce relevant test data. Using deep reinforcement learning (DRL), we introduce a self-learning mechanism to the game testing framework. With DRL, the framework is capable of exploring and/or exploiting the game mechanics based on a user-defined, reinforcing reward signal. As a result, test coverage is increased and unintended game play mechanics, exploits and bugs are discovered in a multitude of game types. In this paper, we show that DRL can be used to increase test coverage, find exploits, test map difficulty, and to detect common problems that arise in the testing of first-person shooter (FPS) games.