Preference-conditioned Pixel-based AI Agent For Game Testing

TL;DR

This paper introduces a pixel-based game testing AI agent that explores environments conditioned on user preferences, using imitation learning to improve exploration and test quality in complex open-world games.

Contribution

It presents a novel preference-conditioned pixel-based agent and an imitation learning method combining self-supervised and supervised objectives for improved game testing.

Findings

Outperforms state-of-the-art pixel-based testing agents in exploration coverage

Achieves higher test execution quality in complex environments

Demonstrates effective preference conditioning in exploration behaviors

Abstract

The game industry is challenged to cope with increasing growth in demand and game complexity while maintaining acceptable quality standards for released games. Classic approaches solely depending on human efforts for quality assurance and game testing do not scale effectively in terms of time and cost. Game-testing AI agents that learn by interaction with the environment have the potential to mitigate these challenges with good scalability properties on time and costs. However, most recent work in this direction depends on game state information for the agent's state representation, which limits generalization across different game scenarios. Moreover, game test engineers usually prefer exploring a game in a specific style, such as exploring the golden path. However, current game testing AI agents do not provide an explicit way to satisfy such a preference. This paper addresses these limitations by proposing an agent design that mainly depends on pixel-based state observations while exploring the environment conditioned on a user's preference specified by demonstration trajectories. In addition, we propose an imitation learning method that couples self-supervised and supervised learning objectives to enhance the quality of imitation behaviors. Our agent significantly outperforms state-of-the-art pixel-based game testing agents over exploration coverage and test execution quality when evaluated on a complex open-world environment resembling many aspects of real AAA games.