DYNAMIC ANALYSIS AND MONITORING OF AI BEHAVIOR IN A MILITARY SIMULATION ENVIRONMENT USING MACHINE LEARNING TECHNIQUES IN THE ARMA 3 SIMULATOR

Mihai DAN

Abstract


This study examines the behavior of artificial intelligence in a military simulation environment, focusing on structural stability and temporal dynamics. While AI is widely implemented in simulation platforms, fewer studies investigate how its behavior evolves over time under controlled conditions. The research analyzes AI performance in the Arma 3 simulator using machine learning techniques applied to server-generated telemetry data, including clustering and temporal comparison. The results show distinct differences between skill-based configurations and advanced tactical logic, highlighting the role of tactical mechanisms in shaping behavioral dynamics. This study forms part of a broader doctoral research program, with limitations related to the specificity of the analysed scenarios and simulation environment.

Full Text:

PDF

References


Zhu, J.-Q., Peterson, J.C., Enke, B., Griffiths, T.L., Capturing the Complexity of Human Strategic Decision-Making with Machine Learning, PsyArXiv, 2024. Available: https://osf.io/preprints/psyarxiv/2squk_v1

Uludağlı, M.Ç., Oğuz, K., Non-player Character Decision-Making in Computer Games, Artificial Intelligence Review, Springer, 2023.

Lu, X., Zhang, J., Chai, Y., Ling, L., behaviour-determining AI in Computer Games: A Literature Review, Applied and Computational Engineering, vol. 174, pp. 193–201, 2025.

del Bosque, A., The Role of Artificial Intelligence in Gaming, Applied Sciences, vol. 15, no. 23, Article 12358, 2025.

Frank, A.B., Gaming AI without AI, Journal of Defense Modelling and Simulation, Sage Publications, 2022.

Hu, C., Zhao, Y., Wang, Z., Du, H., Liu, J., Games for Artificial Intelligence Research: A Review and Perspectives, arXiv:2304.13269, 2024.

Yannakakis, G.N., Togelius, J., Artificial Intelligence and Games, 2nd ed. (public draft), Springer, 2024.

Ao, J., Wu, F., Wu, Y., Swikir, A., Haddadin, S., LLMs as BT-Planner: Leveraging LLMs for behaviour Tree Generation in Robot Task Planning, arXiv:2409.10444, 2024.

Li, F., Wang, X., Li, B., Wu, Y., Wang, Y., Yi, X., A Study on Training and Developing Large Language Models for behaviour Tree Generation, arXiv:2401.08089, 2024.

Paduraru, C., Paduraru, M., Automatic Difficulty Management and Testing in Games using a Framework Based on behaviour Trees and Genetic Algorithms, Proceedings of ICECCS, pp. 170–179, 2019.

Styrud, J., Iovino, M., Norrlöf, M., Björkman, M., Smith, C., Automatic behaviour Tree Expansion with LLMs for Robotic Manipulation, arXiv:2409.13356, 2024.

Kapoor, S., Stroebl, B., Siegel, Z.S., Nadgir, N., Narayanan, A., AI Agents That Matter, arXiv:2407.01502, 2024.

Meister, C., Cotterell, R., Language Model Evaluation Beyond Perplexity, Proceedings of ACL-IJCNLP, pp. 5328–5339, 2021.

Hu, E.J., et al., LoRA: Low-Rank Adaptation of Large Language Models, International Conference on Learning Representations (ICLR), 2022.

Zmădu, R.-G., Pătrașcu, P., Stanciu, C.-O., Modelling Military Action by Using Artificial Intelligence, Romanian Review of Intelligence Studies, vol. 35, no. 3, 2025.

Douze, M., et al., The Faiss Library, arXiv:2401.08281, 2024.

Johnson, J., Douze, M., Jégou, H., Billion-scale similarity search with GPUs, IEEE Transactions on Big Data, vol. 7, no. 3, pp. 535–547, 2019.

Oyelere, S.S., et al., Exploring the Trends of Educational Virtual Reality Games: A Systematic Review, Smart Learning Environments, Springer, 2020.

Grattafiori, A., et al., The Llama 3 Herd of Models, arXiv:2407.21783, 2024.

Zotero, location of the data from servers https://doi.org/10.5281/zenodo.1861975.

Vcom AI V3.4.0, Dominic, https://steamcommunity.com/sharedfiles/filedetails/?id=721359761


Refbacks

  • There are currently no refbacks.


JOURNAL INDEXED IN :