Oyun Teorisi Perspektifinden Bilgisayar Oyunlarında Yapay Zekâ Kullanımı Üzerine Bir Değerlendirme

Yıl 2024, Cilt: 11 Sayı: 1, 422 - 441, 17.05.2024

Ahmet Efe

https://doi.org/10.17336/igusbd.927479

Öz

Yapay zekâ (YZ), oyun ve oyun teorisi, son derece farklı ancak birbiriyle yakından ilişkili disiplinlerdir. Oyun Teorisi, adından oldukça farklı olarak, bir YZ modelinin yapılandırılması ve planlanması söz konusu olduğunda uğraşılması gereken ciddi bir mesele haline gelmiştir. Bununla birlikte, YZ’deki oyun teorisinin gücünü anlamak için, oyun teorisini ve uygulamalarını gerçekte neyin oluşturduğunun temellerini anlamak önem arz etmektedir. Son araştırmalar, bu alanlar arasındaki bağlantıların derin olduğunu ve bu araştırma disiplinleri arasındaki boşluğu doldurmanın zamanının geldiğini göstermektedir. Bu nedenle YZ tabanlı bilgisayar oyunlarının tasarlanması ve geliştirilmesi, çeşitli disiplinlerden profesyonellerin dahil olabileceği karmaşık bir inovasyon olabilir. Buna göre, bir bilgisayar oyununun farklı bölümlerinde oyun tasarımını desteklemek için YZ tabanlı oyun teorisinin kullanımı incelenerek bilgisayar oyunları, oyun teorisi ve YZ arasındaki ilişkinin bir fotoğrafı çekilmektedir. Bu çalışmada, YZ’nin kullandığı doğrusal makine öğrenimi, doğası gereği büyük ölçüde tek boyutlu unsurlarla ilgilenirken, YZ’nin gerçek gücünün aslında oyun teorisini ve bunun çeşitli yönlerini uygulamasıyla ortaya çıkabildiği ileri sürülmektedir.

Anahtar Kelimeler

Oyun Teorisi, Bilgisayar Oyunları, Yapay Zekâ, Makine Öğrenmesi, Nash Dengesi

An Evaluation on the Use of Artificial Intelligence in Computer Games from Perspective of the Game Theory

Öz

Artificial intelligence (AI), game and game theory are extremely different but closely related disciplines. Game Theory, quite different from its name, has become a serious issue to deal with when it comes to configuring and planning an AI model. However, to understand the power of game theory in AI, it is important to understand the basics of what actually makes up game theory and its applications. Recent research shows that the links between these fields are deep and it is time to bridge the gap between these research disciplines. Therefore, designing and developing AI-based computer games can be a complex innovation that can involve professionals from a variety of disciplines. Accordingly, here is a photograph of the relationship between computer games, game theory and AI by examining the use of AI-based game theory to support game design in different parts of a computer game. In this study, it is suggested that while linear machine learning used by AI deals with one-dimensional elements to a great extent by its nature, the real power of AI can actually be revealed by its application of game theory and its various aspects.

Anahtar Kelimeler

Game Theory, Computer Games, Artificial Intelligence, Machine Learning, Nash Equilibrium

Kaynakça

• BINMORE, K. (2007). Playing for real: A text on game theory. Oxford University Press.
• BOWLING, M., BURCH, N., JOHANSON, M., & TAMMELIN, O. (2003). Solving heads-up limit Texas hold'em. In Proceedings of the 18th International Joint Conference on Artificial Intelligence (IJCAI).
• CHAUDHURI S., KANNAN S., MAJUMDAR R., and MICHAEL J. (2017) Game Theory in AI, Logic, and Algorithms, Dagstuhl Reports, Vol. 7, Issue 3, pp. 27–32 Wooldridge Dagstuhl Reports Schloss Dagstuhl – Leibniz-Zentrum für Informatik, Dagstuhl Publishing, Germany
• COHEN-SOLAL, Q., (2020) “Learning to Play Two-Player Perfect-Information Games without Knowledge, https://arxiv.org/abs/2008.01188
• DARRYL C., (2003). Enhancing gameplay: challenges for artificial intelligence in digital games.
• FUDENBERG, D., & LEVINE, D. K. (1999). The Theory of Learning in Games. MIT Press.
• FUDENBERG, D., & TIROLE, J. (1991). Game theory. MIT press.
• GARISTO D., (2019) Google AI beats top human players at strategy game StarCraft II, Nature, https://www.nature.com/articles/d41586-019-03298-6
• GENÇ S. Y., KADAH H. (2018) Oyun Teorisi ve Nash’in Denge Stratejisi, Iğdır Üniv Sos Bil Der, http://sosbilder.igdir.edu.tr/DergiTamDetay.aspx?ID=534&Detay=Ozet
• GRÜNWALD, Peter D.; DAWID, A. (2004) Philip. Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory. Ann. Statist. 32, no. 4, 1367--1433. doi:10.1214/009053604000000553. https://projecteuclid.org/euclid.aos/1091626173
• HART, S., & MAS-COLELL, A. (2013). Bargaining and cooperation in strategic form games. Journal of the European Economic Association, 11(4), 738-750.
• LAMBERT, T., EPELMAN, M. A., & SMITH, R. L. (2005). A Fictitious Play Approach to Large-Scale Optimization. Operations Research, 53 (3), 477–489.
• LECUN, Y., BENGIO, Y., & HINTON, G. (2015). Deep learning. Nature, 521(7553), 436-444.
• LI, Y., CARBONI, G., GONZALEZ, F. et al. (2019). Differential game theory for versatile physical human–robot interaction. Nat Mach Intell 1, 36–43 https://doi.org/10.1038/s42256-018-0010-3
• LIANG X., XIAO Y., (2010) Studying Bio-Inspired Coalition Formation of Robots for Detecting Intrusions Using Game Theory, in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), vol. 40, no. 3, pp. 683-693, June, doi: 10.1109/TSMCB.2009.2034976.
• LIPTON, Z. C., BERKOWITZ, J., & ELKAN, C. (2015). A critical review of recurrent neural networks for sequence learning. arXiv preprint arXiv:1506.00019.
• MYERSON, R. B. (1991). Game theory: Analysis of conflict. Harvard University Press.
• NOWAK M. A. and SIGMUND K., (2004) Evolutionary dynamics of biological games,” Science, vol. 303, no. 5659, pp. 793–799.
• NOWAK, M. A. (2006). Five rules for the evolution of cooperation. Science, 314(5805), 1560-1563.
• NOWÉ A., VRANCX P., De HAUWERE YM. (2012) Game Theory and Multi-agent Reinforcement Learning. In: Wiering M., van Otterlo M. (eds) Reinforcement Learning. Adaptation, Learning, and Optimization, vol 12. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-27645-3_14
• OSBORNE, M. J., & RUBINSTEIN, A. (1994). A course in game theory. MIT press.
• PETROVSKIY M., (2004) "A game theory approach to pairwise classification with support vector machines," 2004 International Conference on Machine Learning and Applications, Proceedings., Louisville, KY, USA, 2004, pp. 115-122, doi: 10.1109/ICMLA.2004.1383502.
• PROSSER, M, (2019). What Games Are Humans Still Better at Than AI?, Singularity Hub, https://singularityhub.com/2019/02/10/what-games-are-humans-still-better-at-than-ai/
• RASMUSEN, E. (2007). Games and information: An introduction to game theory. Wiley.
• RIPLEY, B. (2000). Pattern Recognition and Neural Networks. Cambridge University Press.
• SHOHAM, Y. (2008). Computer science and game theory. Communications of the ACM, 51(8), 75-79.
• SILVER, D., HUANG, A., MADDISON, C. J., GUEZ, A., SIFRE, L., VAN DEN DRIESSCHE, G., ... & HASSABIS, D. (2016). Mastering the game of Go with deep neural networks and tree search. Nature, 529(7587), 484-489.
• STATT, N., (2019) How Artificial Intelligence Will Revolutionize The Way Video Games Are Developed and Played, Theverge, https://www.theverge.com/2019/3/6/18222203/video-game-ai-future-procedural-generation-deep-learning
• SUTTON, R. S., & BARTO, A. G. (2018). Reinforcement learning: An introduction. MIT press Cambridge.
• TENNENHOLTZ M., (2002) “Game theory and artificial intelligence,” in Foundations and Applications of Multi-Agent Systems, M. d’Inverno, M. Luck, M. Fisher, and C. Preist, Eds., vol. 2403 of Lecture Notes in Computer Science, pp. 34–52, Springer, Berlin, Germany.
• WOLPERT, D. H. (2004). Information Theory - The Bridge Connecting Bounded Rational Game Theory and Statistical Physics. arXiv.org:cond-mat/0402508 .
• YANNAKAKIS, G. N., & HALLAM, J. (2018). Artificial intelligence for games. CRC Press.
• ZHANG, C., & FALTINGS, B. (2019). Nash equilibrium learning for autonomous agents. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3210-3217.