EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Learning to Play Like Humans: A Deep Neural Framework for Believable Agent Development in Virtual Worlds

Naveed Anwer Butt, Kiran Shahzadi, Mian Muhammad Awais, Julien Brito Ballester, Carmen Lili Rodriguez Velasco, Nagwan Abdel Samee, Imran Ashraf

Computer Animation and Virtual Worlds · 2026-11 · 37 (6)

DOI: 10.1002/cav.70185 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Animation and Virtual Worlds, online erschienen am 20.11.2026. Verfasst von Naveed Anwer Butt und 6 weiteren Autor:innen. Die Arbeit nennt 72 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Many existing intelligent agents still behave in a mechanical way leading to user dissatisfaction and lack of engagement. To create more realistic and accurate imitations, this study proposes an imitation learning framework that explores deep learning (DL) and traditional machine learning, to build a computational model. The approach is tested using two case studies: Pac‐Man to predict human behavior, and Player Unknown's Battlegrounds (PUBG) to evaluate how well the model could imitate it. Recurrent neural networks (RNN), gated recurrent units, long short‐term memory networks (LSTM), random forest, extreme gradient boosting (XGBoost), etc. To assess model performance, mean squared error, root mean squared error, and accuracy are used. Among the employed models, RNN and LSTM achieved near‐identical and highest accuracy on Pac‐Man (99.98% and 99.96% on the combined dataset), clearly ahead of GRU, random forest and XGBoost, while XGBoost performed best on PUBG with 97.37% accuracy. A dedicated discussion explains why RNN performs well in the low‐dimensional, short‐horizon Pac‐Man setting and lists its advantages and limitations. The Mann–Whitney U Test and the Cosine similarity tests are also applied to measure how believable the imitated behaviors were. Neither analysis detected a statistically significant difference between human and model traces, and cosine similarity was approximately 0.98.

Zitieren

APA

Butt, N. A., Shahzadi, K., Awais, M. M., Ballester, J. B., Velasco, C. L. R., Samee, N. A., & Ashraf, I. (2026). Learning to Play Like Humans: A Deep Neural Framework for Believable Agent Development in Virtual Worlds. Computer Animation and Virtual Worlds, 37(6). https://doi.org/10.1002/cav.70185

Vancouver

Butt NA, Shahzadi K, Awais MM, Ballester JB, Velasco CLR, Samee NA, et al. Learning to Play Like Humans: A Deep Neural Framework for Believable Agent Development in Virtual Worlds. Computer Animation and Virtual Worlds. 2026;37(6). doi:10.1002/cav.70185

BibTeX
@article{Butt2026,
  author = {Butt, Naveed Anwer and Shahzadi, Kiran and Awais, Mian Muhammad and Ballester, Julien Brito and Velasco, Carmen Lili Rodriguez and Samee, Nagwan Abdel and Ashraf, Imran},
  title = {Learning to Play Like Humans: A Deep Neural Framework for Believable Agent Development in Virtual Worlds},
  journal = {Computer Animation and Virtual Worlds},
  year = {2026},
  volume = {37},
  number = {6},
  doi = {10.1002/cav.70185}
}
Kostenlos starten →