CA2: Code-Aware Agent for Automated Game Testing

TL;DR

CA2 introduces a code-aware reinforcement learning agent that leverages call stack information to improve automated game testing effectiveness and coverage.

Contribution

The paper presents CA2, a novel RL-based game testing agent that uses internal code signals like call stacks to enhance testing strategies.

Findings

CA2 outperforms non-code aware baselines in test effectiveness.

Incorporating call stack information improves targeted testing.

CA2 is effective in both state-based and image-based environments.

Abstract

Automated game testing is important for verifying game functionality, but it remains a costly and time-consuming process. Manual testing often misses edge cases, and current automated methods struggle to provide full code coverage. Prior work has explored reinforcement learning (RL) for game testing, but without leveraging internal code signals such as the call stack. We present Code Aware Agent (CA2), which uses call stack information to learn effective testing strategies. The agent receives the current function call trace along with the game state and learns to reach specific target functions. We instrument two types of environments, 1) State-based and 2) Image-based, with support for efficient call stack extraction. Through experimental evaluation, we find that CA2 achieves consistent improvement over the non-code aware baselines, which does not leverage call stack information. Our results show that incorporating code signals like the call stack enables more effective and targeted game testing.