AI vs. AI: comparing artificial intelligence with actual intelligence for a gameplay task

Simple item page
dc.contributor.authorAycock, John
dc.contributor.authorBiittner, Katie
dc.contributor.authorKhaleel, Syeda Zainab
dc.contributor.authorTherrien, Carl
dc.contributor.authorQuerengesser, Allie
dc.contributor.authorSikstrom, Hailey
dc.date.accessioned2026-01-22T15:56:32Z
dc.date.available2026-01-22T15:56:32Z
dc.date.issued2025
dc.descriptionPresented on August 27, 2025, at the IEEE Conference on Games in Lisbon, Portugal.
dc.description.abstractIs 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.
dc.description.urihttps://macewan.primo.exlibrisgroup.com/permalink/01MACEWAN_INST/1mogj0i/cdi_ieee_primary_11114144
dc.identifier.doihttps://doi.org/10.1109/CoG64752.2025.11114144
dc.identifier.urihttps://hdl.handle.net/20.500.14078/4118
dc.language.isoen
dc.rightsAll Rights Reserved
dc.subjectAI
dc.subjectreinforcement learning
dc.subjectuser studies
dc.subjectcode coverage
dc.subjectreverse engineering
dc.subjectAtari 2600
dc.titleAI vs. AI: comparing artificial intelligence with actual intelligence for a gameplay tasken
dc.typePresentation

Files

Collections

Department of Anthropology, Economics and Political Science