AI vs. AI: Comparing Artificial Intelligence with Actual Intelligence for a Gameplay Task
Is AI always the best choice for every task? We conducted two user studies, one large-scale and one small-scale, to attempt a testing-related gameplay task, where the goal was to maximize the code and data coverage of a set of Atari 2600 games. This particular problem was previously addressed using an AI-based system published by Ganesh et al. in the 2023 IEEE Conference on Games. Our new, human-derived results not only replicate the coverage shown in the previous AI-based study, but more importantly, by using humans for gameplay we were able to get those results with much less time, effort, and resources.
Authors
- Katie Biittner (ORCID: https://orcid.org/0000-0003-2353-8252)
- John Aycock (ORCID: https://orcid.org/0000-0003-0352-489X)
- Carl Therrien (ORCID: https://orcid.org/0000-0002-0634-7633)
- Syeda Zainab Khaleel
- Allie Querengesser
- Hailey Sikstrom
Institutions
- University of Calgary (CA)
- MacEwan University (CA)
Publication Details
- Published
- 2025-08-19
- DOI
- https://doi.org/10.1109/cog64752.2025.11114144
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Social Sciences and Humanities Research Council of Canada