Rule-Based Sports Game Framework for Creating Sports Game AI Models: Focusing on Soccer Games
1
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
With the development of Deep Learning (DL), artificial intelligence (AI) models are being created and used in various fields today. Today, with the development of computers and DL algorithms, DL-based AI models can learn a lot of data and find rules by themselves. DeepMind's Alphago shows the possibility of self-determination of game rules and high-level game play with only learning data. Although these various DL algorithms are applied to the game field, there are limits to successful play with only a single AI model in areas where team tactics and individual play coexist, such as sports games. Today, high-quality sports games are readily available. However, game AI researchers may need to receive game code sources or provide test simulators from game companies in order to develop AI models suitable for such high-quality sports games. In order for game AI researchers to develop AI models in the field of active sports games, a test environment that reflects the rules and characteristics of sports games and is easy to access is required. In this paper, we propose a rule-based soccer game framework that can create and test AI models in sports games where team tactics and individual play are important
Abstract
With the development of Deep Learning (DL), artificial intelligence (AI) models are being created and used in various fields today. Today, with the development of computers and DL algorithms, DL-based AI models can learn a lot of data and find rules by themselves. DeepMind's Alphago shows the possibility of self-determination of game rules and high-level game play with only learning data. Although these various DL algorithms are applied to the game field, there are limits to successful play with only a single AI model in areas where team tactics and individual play coexist, such as sports games. Today, high-quality sports games are readily available. However, game AI researchers may need to receive game code sources or provide test simulators from game companies in order to develop AI models suitable for such high-quality sports games. In order for game AI researchers to develop AI models in the field of active sports games, a test environment that reflects the rules and characteristics of sports games and is easy to access is required. In this paper, we propose a rule-based soccer game framework that can create and test AI models in sports games where team tactics and individual play are important
참고문헌 (19)
- LECUN, Yann, "Deep learning", nature, 521(7553), pp.436~444 (2015)
- DAVIS, Randall, "Rule-based expert systems: The MYCIN experiments of the Stanford Heuristic Programming Project" (1984)
- WANG, Fei-Yue, "Where does AlphaGo go : From church-turing thesis to AlphaGo thesis and beyond", IEEE, 2016, pp.3(2), 113~120
- KAELBLING, Leslie Pack, "Reinforcement learning : A survey", Journal of artificial intelligence research, 4, pp.237~285 (1996)
- ZHAO, Yunqi, "On multi-agent learning in team sports games" (2019)
- Seongjin Hong, "Development of performance determinants criteria for evaluation of soccer players by position", Sports Science Research, 21(2), pp.1172~1182 (2010)
- Deokki Ahn, "Changes in sports game character development for next-generation console game consoles: Focusing on EA's next-generation sports game FIFA 14", Journal of Integrated Design Research, 13(1), pp.9~20 (2014)
- FIALHO, Gabriel, "Predicting sports results with artificial intelligence –a proposal framework for soccer games", Procedia Computer Science, 164, pp.131~136 (2019)
- LEE, David, "Principles and methods of testing finite state machines-a survey", Proceedings of the IEEE, 84(8), pp.1090~1123 (1996)
- RAMYACHITRA, D, "Imbalanced dataset classification and solutions : a review", International Journal of Computing and Business Research(IJCBR), 5(4), pp.1~29 (2014)
- ARYA, Sunil, "An optimal algorithm for approximate nearest neighbor searching fixed dimensions", Journal of the ACM(JACM), 45(6), pp.891~923 (1998)
- IERUSALIMSCHY, Roberto, "Programming in lua" (2006), Roberto Ierusalimschy
- MYLES, Anthony J., "An introduction to decision tree modeling", Journal of Chemometrics : A Journal of the Chemometrics Society, 18(6), pp.275~285 (2004)
- Jo Dal-ho, "A method for controlling defensive NPCs in soccer games using decision tree learning algorithms", Journal of the Korean Game Society, 11(6), pp.61~70 (2011)
- TRINH, Hoang, "Detecting human activities in retail surveillance using hierarchical finite state machine", 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp.1337~1340 (2011), IEEE
- Kyungjin Baek, "Design and implementation of artificial intelligence agent for real-time simulation soccer game in mobile environment", Korean Information Processing Society Conference Proceedings, 23(1), pp.636~639 (2016)
- YAO, Xin, "A review of evolutionary artificial neural networks", International journal of intelligent systems, 8(4), pp.539~567 (1993)
- 김향화, "동적 상태 진화 신경망에 기반한 팀 에이전트의 진화", 멀티미디어학회논문지, 12(2), pp.290~299 (2009), 한국멀티미디어학회
- GU, Bonwoo, "UX Framework Including Imbalanced UX Dataset Reduction Method for Analyzing Interaction Trends of Agent Systems", Sensors, 23(3), pp.1651~ (2023)