Journal of the Korea Society of Computer and Information (한국컴퓨터정보학회논문지)

Korean Society of Computer Information (한국컴퓨터정보학회)
권호 표지
DOI QR코드

DOI QR Code

Utilization of Simulation and Machine Learning to Analyze and Predict Win Rates of the Characters Battle

  • Kang, Hyun-Syug (Dept. of Computer Science, Gyeongsang National University)
  • Received : 2020.06.04
  • Accepted : 2020.07.14
  • Published : 2020.07.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recently, for designing virtual characters in the battle game field effectively, some methods are very needed to predicate the win rates of the battle of them efficiently. In this paper, we propose a method to solve this problem by combining simulation and machine learning. Firstly, a simulation is used to analyze the win rates of the battle of virtual characters in the battle game. In addition, we apply a regression model based machine learning scheme to predict win rates of the battle of virtual characters according to their abilities. Our experimental results using suggested method show that it is almost no difference between the win rates of the simulation and the prediction results using the machine learning scheme. And also, we can obtain good performance in the experiment using only simple regression based machine learning model.

최근, 대전 게임 분야에서, 가상 캐릭터들의 효과적인 설계를 위해 캐릭터의 승률을 효율적으로 예측할 수 있는 방법들이 매우 필요하다. 우리는 본 논문에서 이 문제를 해결하기 위해 시뮬레이션과 기계 학습을 결합하는 방법을 제안한다. 우선 대전 게임에서 가상 캐릭터의 대전 승률을 분석하기 위해서 시뮬레이션을 사용하고, 가상 캐릭터의 능력치에 따라서 승률을 예측하기 위해 회귀 모델에 기반한 기계 학습 기법을 적용한다. 제안한 기법으로 실험한 결과는 시뮬레이션 결과로 나온 승률과 기계 학습 기법이 예측한 승률이 거의 차이가 없다는 것을 확인하였다. 그리고 간단한 회귀 모델에 기반한 기계 학습으로도 실험에서 좋은 성능을 얻을 수 있었다.

Keywords

References

  1. Schwab. K., "The Fourth Industrial Revolution: What It Means, How To Respond," World Economic Forum, 14 Jan 2016. www.weforum.org.
  2. Department of Defense(USA), "Modeling and Simulation(M&S) Verification, Validation, and Accreditation(VV&A)," DoD Instruction 5000.61, Oct 15, 2018.
  3. The Korea Society for Simulation, "Topic: Simulation and Artifi cial intelligence", Dec 2018.
  4. Roohi, S., Takatalo, J., Guckelsberger, C., and Hamalainen, P., "Review of Intrinsic Motivation in Simulation-based Game Testing." In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pp. 1-13. Apr 2018. DOI: https://dl.acm.org/doi/10.1145/3173574.3173921
  5. Guerrero-Romero, C., Lucas, S. M., and Perez-Liebana, D., "Using a Team of General AI Algorithms to Assist Game Design and Testing." In 2018 IEEE Conference on Computational Intelligence and Games, pp. 1-8, Aug 2018. DOI:https://www.researchgate.net/publication/328308938
  6. Tag-Gon Kim, “M & S Engineering,” The Korean Institute of Information Scientists and Engineers, Vol. 25, No. 11, pp. 5-15, Nov 2007. DOI:https://www.koreascience.or.kr/article/JAKO200735822312725.page
  7. Si-Heon Kim, "Agent-Based Modeling and Simulation Methodo logy using Social-Level Characteristics: A Case Study on Self-Adaptive Smart Grid and Military Domain Systems using Tropos," Journal of KIISE, Vol. 42, No. 12, pp. 1503-1521, Dec 2015. DOI:https://www.koreascience.or.kr/article/JAKO201502648775165.page https://doi.org/10.5626/JOK.2015.42.12.1503
  8. The AnyLogic Company, "What is AnyLogic?", 2018. www.anylogic.com,
  9. Freedman. D. A., "Statistical Models: Theory and Practice", Cambridge University Press, 26, 2009.
  10. Cox. D. R., "The Regression Analysis of Binary Sequences," Journal of the Royal Statistical Society, Vol. 20, No. 2, pp. 215-242, 1958. DOI:https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/j.2517-6161.1958.tb00292.x
  11. Google Colab, "Hello, Colaboratory", 2018. https://colab.research.google.com.
  12. The Pytorch Company, "From Research To Production", 2018. https://pytorch.org/.
  13. Krizhevsky. A,, Sutskever. I,, and Hinton. G. E., "Imagenet Classification with Deep Convolutional Neural Networks," In Advances in Neural Information Processing Systems(NIPS), pp. 1106-1114, 2012. DOI:http://papers.nips.cc/paper/4824-imagene t-classification-with-deep-convolutional-neural-networ
  14. Seong-hun Kim, "A Machine Learning For Everyone - Deep Learning Lectures", 2016. https://hunkim.github.io/ml/.