Many-Objective Neuroevolution for Testing Games

2025-01-14

AI Summary

Game testing suffers from low coverage and poor efficiency due to high stochasticity and hard-to-reach states. To address this, we propose the first multi-objective neural evolutionary test generation framework specifically designed for game testing. Our approach innovatively integrates NEATEST, MIO, and MOSA into a unified multi-objective optimization paradigm and enhances the NEWS/D algorithm to avoid search stagnation caused by unreachable states. Empirical evaluation on 20 Scratch programs demonstrates that our method significantly improves average branch coverage from 75.88% to 81.33% while reducing search time by 93.28%. This work constitutes the first systematic application of multi-objective neural evolution to game testing, offering a novel, empirically validated methodology for automated testing of highly uncertain software systems.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Reasoning under Uncertainty: Stochastic Optimization
• Machine Learning: Evolutionary Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Web data generation and simulation

Abstract

Generating tests for games is challenging due to the high degree of randomisation inherent to games and hard-to-reach program states that require sophisticated gameplay. The test generator NEATEST tackles these challenges by combining search-based software testing principles with neuroevolution to optimise neural networks that serve as test cases. However, since NEATEST is designed as a single-objective algorithm, it may require a long time to cover fairly simple program states or may even get stuck trying to reach unreachable program states. In order to resolve these shortcomings of NEATEST, this work aims to transform the algorithm into a many-objective search algorithm that targets several program states simultaneously. To this end, we combine the neuroevolution algorithm NEATEST with the two established search-based software testing algorithms, MIO and MOSA. Moreover, we adapt the existing many-objective neuroevolution algorithm NEWS/D to serve as a test generator. Our experiments on a dataset of 20 SCRATCH programs show that extending NEATEST to target several objectives simultaneously increases the average branch coverage from 75.88% to 81.33% while reducing the required search time by 93.28%.

Problem

• Game Testing
• Randomness
• Complex Operations

Innovation

• Neuroevolution
• Multi-objective Optimization
• Game Testing