Research and Development of Artificial Intelligence in Electronic Games

Baihan Yu

doi:10.62051/h1y2qe04

Authors

Baihan Yu

DOI:

https://doi.org/10.62051/h1y2qe04

Keywords:

Artificial intelligence; Gaming industry; Deep Learning.

Abstract

This study examines the multiple applications of Artificial Intelligence (AI) technologies in game design and development and their implications. First, this paper outlines the main types of machine learning, including supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning, and introduces deep learning methods such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs). Subsequently, the specific applications of AI in game design are analyzed in detail in the article, encompassing procedural content generation, game balancing, behavioral control of non-player characters (NPCs) and social AI implementation. In game testing and quality assurance, AI technology significantly improves game development efficiency and user experience through automated error detection and user feedback analysis. In addition, AI also shows great potential in adaptive difficulty adjustment and personalized content recommendation, further enhancing players' game experience. In particular, this article also discusses the application of AlphaGo, DeepMind's StarCraft II AI, and OpenAI Five in Dota 2, demonstrating the superior performance of AI in complex gaming environments. Finally, the article discusses the future direction and challenges of AI in gaming, emphasizing the importance of technical security, data privacy, and ethical issues. Overall, AI technology shows great potential in the gaming field, which not only improves the intelligence level of games, but also brings new opportunities and challenges for game development and industry development.

Downloads

Download data is not yet available.

References

[1] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60(6): 84-90.

[2] Amodei D, Olah C, Steinhardt J, Christiano P, Schulman J, Mané D. Concrete problems in AI safety. arXiv preprint arXiv:1606.06565, 2016.

[3] Géron A. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow. O'Reilly Media, 2019.

[4] Goldberg Y. Neural Network Methods for Natural Language Processing. Morgan & Claypool Publishers, 2017.

[5] Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep Learning. MIT Press, 2016.

[6] Silver D, Huang A, Maddison C J, Guez A, Sifre L, Van Den Driessche G, et al. Mastering the game of Go with deep neural networks and tree search. Nature, 2016, 529(7587): 484-489.

[7] Vinyals O, Babuschkin I, Czarnecki W M, Mathieu M, Dudzik A, Chung J, et al. Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature, 2019, 575(7782): 350-354.

[8] Berner C, Brockman G, Chan B, Cheung V, Debiak P, Dennison C, et al. Dota 2 with large scale deep reinforcement learning. arXiv preprint arXiv:1912.06680, 2019.

[9] Justesen N, Bontrager P, Togelius J, Risi S. Deep learning for video game playing. IEEE Transactions on Games, 2019, 11(4): 376-399.

[10] El-Nasr M S, Drachen A, Canossa A. Game Analytics: Maximizing the Value of Player Data. Springer, 2013.