Adversarial Behaviour Debugging in a Two Button Fighting Game
2021 IEEE Conference on Games (CoG)(2021)
摘要
We introduce the concept of Adversarial Behaviour Debugging (ABD), using intelligent agents to assist in the debugging of human-authored game AI systems, and Bonobo, an ABD system for Unity. To investigate the differences between ABD and traditional playtesting, we collected gameplay data from Bonobo agents and human testers playing against a buggy AI opponent. We present a comparison of the differences in gameplay and an online study on whether these differences affect observers perceptions of the AI opponent. We found that while there were clear differences, ABD compares favourably to human testing and has the potential to offer a distinct perspective.
更多查看译文
关键词
Games development,debugging,game AI,bugs,testing,neuroevolution
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要