Artificial Intelligence in Video Games: State of the Art and Future Potential
Abstract
Since the beginnings of video games as a creative medium over seven decades ago, artificial intelligence (AI) has played an integral role. However, this form of AI differs significantly from what the general public perceives it to be, as well as from standard definitions found in relevant academic disciplines like data science and machine learning. Recent advancements in these areas—such as the rise of large-scale language models and generative algorithms—have led to convergence between these distinct understandings. As a result, novel possibilities for innovation and creativity emerge in the realm of interactive media. The present article explores the current state-of-the-art and near-future developments in AI-driven gaming technologies. It also addresses key questions: How did video game AI evolve prior to the advent of machine learning? Can newer forms of AI, including machine learning and generative systems, supplant traditional approaches, or will they complement them instead? Do each type have specific uses that set them apart? Finally, what broader implications do these evolving methodologies hold for interactive entertainment moving forward?
Downloads
References
Aelbrecht B., Mojsilovic, J. (2023). AI In The Video Game Industry: Evolution, Implementation, and Impact. Numalis. https://numalis.com/publications-121-ai_in_the_video_game_industry_evolution_implementation_and_impact.php
Badia, A., P., Piot, B., Kapturowski, S., Sprechmann, P., Vitvitskyi, A., Guo, D., Blundell, C. (2020). Agent57: Outperforming the Atari Human Benchmark. https://doi.org/10.48550/arXiv.2003.13350
Burke, J. (2023). What are the risks and limitations of generative AI?. TechTarget. https://www.techtarget.com/searchenterpriseai/tip/What-are-the-risks-and-limitations-of-generative-AI
Farr, G.E., Powell, D.R. (1999). Unsupervised Learning in Metagame. Advanced Topics in Artificial Intelligence. Lecture Notes in Computer Science. 1747 https://doi.org/10.1007/3-540-46695-9_3
Gillis, A. (2023). Supervised Learning. TechTarget. https://www.techtarget.com/searchenterpriseai/definition/supervised-learning
Gillis, A. (2023). Unsupervised Learning. TechTarget. https://www.techtarget.com/searchenterpriseai/definition/unsupervised-learning
Hornik, K., Stinchcombe, M., White, H. (1989). Multilayer feedforward networks are universal approximators. J Neural Networks 2(5), 359-366. https://doi.org/10.1016/0893-6080(89)90020-8
Hovsepyan, T. (2022). Machine Learning in Gaming. PlatAI. https://plat.ai/blog/machine-learning-in-gaming/. Accessed 3 November 2024
Lillicrap, T., Hunt, J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., Wierstra, D. (2015). Continuous control with deep reinforcement learning. arXiv preprint. arXiv:1509.02971.
Manh Toan, H. (2024). Regulating generative AIs: (Re)defining video games as cultural products. J AI & Society. https://doi.org/10.1007/s00146-024-02034-7
Minaee, S., Mikolov, T., Nikzad, N., Chenaghlu, M., Socher, R., Amatriain, X., Gao, J. (2024). Large Language Models: A Survey. arXiv preprint. arXiv:2303.18223
Mnih, V., et al. (2015). Human-level control through deep reinforcement learning. Nature. 518, 7540, 529-533. https://doi.org/10.1038/nature14236
Prince-Tritto, P., Ponce, H. (2024). Exploring the Challenges and Limitations of Unsupervised Machine Learning Approaches in Legal Concepts Discovery. In: Advances in Soft Computing, MICAI 2023. Lecture Notes in Computer Science, 14392, 52-67 https://doi.org/10.1007/978-3-031-47640-2_5
Roose, K. (2022). An A.I.-Generated Picture Won an Art Prize. Artists Aren’t Happy. The New York Times. https://www.nytimes.com/2022/09/02/technology/ai-artificial-intelligence-artists.html
Salian, I. (2021). ‘Paint Me a Picture’: NVIDIA Research Shows GauGAN AI Art Demo Now Responds to Words. Nvidia. https://blogs.nvidia.com/blog/gaugan2-ai-art-demo/
Sarker, I. (2021). Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN Comput Sci 2, 420. https://doi.org/10.1007/s42979-021-00815-1
Shumakova, N.I., Lloyd J.J., Titova E.V. (2023). Towards Legal Regulations of Generative AI in the Creative Industry. Journal of Digital Technologies and Law. 1(4), 880-908. https://doi.org/10.21202/jdtl.2023.38
Totilo, S. (2024). AI video game NPCs can be fun to chat with, but there's a big financial catch. Game File. https://www.gamefile.news/p/ai-npcs-ubisoft-convai-money
Tshilidzi, M. (2024). The Limitations of Maximum Likelihood Estimation in Generative AI: An Obstacle to Representing Rare Information. UNU Centre. https://unu.edu/article/limitations-maximum-likelihood-estimation-generative-ai-obstacle-representing-rare
van Hasselt, H., Guez, A., Silver, D. (2015). Deep reinforcement learning with double Q-learning. arXiv preprint. arXiv:1509.06461
Walsh, D. (2023). The legal issues presented by generative AI. Ideas Made to Matter. https://mitsloan.mit.edu/ideas-made-to-matter/legal-issues-presented-generative-ai
Wang, Z. et al. (2015). Dueling network architectures for deep reinforcement learning. arXiv preprint. arXiv:1511.06581
Copyright (c) 2025 HSE University
This work is licensed under a Creative Commons Attribution 4.0 International License.
