🤖 AI Summary
This work addresses the reliance on manual, repetitive testing to uncover behavioral vulnerabilities in goalkeeper AI within game development by proposing a multi-agent automated testing framework based on iterative reinforcement learning. The approach incorporates a reward adaptation mechanism into existing reinforcement learning algorithms, effectively mitigating policy overfitting and enabling the continuous discovery of diverse, high-quality vulnerability-inducing strategies. Experimental results demonstrate that a single run of the framework automatically identifies six distinct vulnerability strategies comparable in quality to those found through hours of manual testing, significantly enhancing both testing efficiency and coverage diversity.
📝 Abstract
Testing is a major effort for the gaming industry, requiring a significant part of development budget and people power. We present a case study on a development version of the ice hockey game EA SPORTS NHL 26, for which human playtesters test the goalie AI for behavioral exploits. To reduce the effort of re-testing the goalie AI after every game or behavior modification in the development phase, we propose Reward-Adaptive Iterative Discovery (RAID), a novel approach to automatically find exploits using an iterative Reinforcement Learning (RL) approach that trains a population of goal scoring agents. While previous approaches can already successfully find exploits, RL algorithms tend to overfit to a single solution. We introduce a simple extension on top of existing RL algorithms, such that they find multiple diverse high-quality solutions. For our first deployment of this approach, within a single experiment we were able to find six hockey scoring exploit strategies that were qualitatively similar to those that playtesters had found in hours-long manual testing sessions.