DOI QR코드

DOI QR Code

Automatic Generation of Match-3 Game Levels using Genetic Algorithm

유전알고리즘을 이용한 Match-3 게임 레벨 자동 생성

  • 박인화 (숭실대학교 미디어학부) ;
  • 오경수 (숭실대학교 미디어학부)
  • Received : 2019.05.13
  • Accepted : 2019.06.12
  • Published : 2019.06.19

Abstract

This paper proposes a automatic generation method of Match-3 game levels through genetic algorithm. It takes a lot of time and effort if persons have to control the level in the game. In this paper, the genetic algorithm is applied to create an appropriate block combination. We create block combination from integer DNA. Fitness is high if success probability played by computer is closer to given probability. Experiments have shown that computer-determined levels of difficulty have a significant impact on the results of game played persons.

본 논문은 유전 알고리즘을 통한 Match-3 게임의 레벨 자동 생성 방법을 제안한다. 적절한 난이도의 게임 레벨을 만들기 위하여 사람이 일일이 게임 레벨을 조절해야 한다면, 사람은 그것을 위한 많은 시간과 노력이 필요하다. 본 논문에서는 유전 알고리즘을 적용하여 Match-3 게임에서의 난이도에 맞는 블록조합을 생성한다. 각 게임 레벨의 블록조합이 진화되는 개체이다. 유전자인 정수로부터 블록조합 개체를 생성하고, 주어진 성공확률과 컴퓨터가 플레이했을 때의 성공확률이 가까워질수록 적합도가 높아지도록 설정하여 해당 블록조합을 진화시킨다. 이를 통해 게임 난이도에 맞는 적절한 블록조합들을 생성하는 데 성공하였으며, 실험한 결과 컴퓨터가 결정한 난이도가 실제 사람이 게임했을 때의 결과에 영향을 준다는 것을 확인하였다.

Keywords

KGOHCL_2019_v19n3_25_f0001.png 이미지

[Fig. 1] Scene about Playing Match-3 Game

KGOHCL_2019_v19n3_25_f0002.png 이미지

[Fig. 2] Block Combination of Stage 1

KGOHCL_2019_v19n3_25_f0003.png 이미지

[Fig. 3] Block Combination of Stage 2

KGOHCL_2019_v19n3_25_f0004.png 이미지

[Fig. 4] Block Combination of Stage 3

[Table 1] Block Combinations by Genetic Algorithm

KGOHCL_2019_v19n3_25_t0001.png 이미지

[Table 2] Success Probability by Played Persons

KGOHCL_2019_v19n3_25_t0002.png 이미지

[Table 3] Comparison of the Average Score According to the Order of Game Stage

KGOHCL_2019_v19n3_25_t0003.png 이미지

References

  1. Krivicich, Alexander Higgins, et al, "Match three gaming system and method", U.S. Patent Application No. 13/494,941, 2013.
  2. Karl Sims, "Evolving virtual creatures", SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques, pp15-22, 1994.
  3. T.E. Revello, R. McCartney, "Generating war game strategies using a genetic algorithm", Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600), 2002.
  4. Sang-Wook Park, Won-Hyung Lee, "Genetic Algorithm for Game Monster Generation", Proceedings of the Korea Contents Associa Conference, Vol. 4, No. 2, pp8 2006.
  5. Teong Joo Ong, Ryan Saunders, John Keyser, John J. Leggett, "Terrain generation using genetic algorithms", Proceeding GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation, pp1463-1470, 2005.
  6. David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, Demis Hassabis, "Mastering the game of Go with deep neural networks and tree search", Nature Vol. 529, pp484-489, 2016. https://doi.org/10.1038/nature16961
  7. Shin-Jin Kang, Seung-Ho Shin, Sung-Hyun Cho, "A Game Level Design Technique Using the eGenetic Algorithms", Journal of The Korea Computer Graphics Society, Vol. 15, No. 4, pp13-21, 2009. https://doi.org/10.15701/kcgs.2009.15.4.13
  8. Sorenson N., Pasquier P., "Towards a Generic Framework for Automated Video Game Level Creation", Applications of Evolutionary Computation. EvoApplications 2010. Lecture Notes in Computer Science, Vol. 6024, Springer, Berlin, Heidelberg, 2010.
  9. Gillian Smith, Jim Whitehead, Michael Mateas, Mike Treanor, Jameka March, Mee Cha, "Launchpad: A Rhythm-Based Level Generator for 2-D Platformers", IEEE Transactions on Computational Intelligence and AI in Games, Vol. 3, No. 1, pp1-16, 2011. https://doi.org/10.1109/TCIAIG.2010.2095855
  10. Nathan Sorenson, Philippe Pasquier, Steve DiPaola, "A Generic Approach to Challenge Modeling for the Procedural Creation of Video Game Levels", IEEE Transactions on Computational Intelligence and AI in Games, Vol. 3, No. 3, pp229-244, 2011. https://doi.org/10.1109/TCIAIG.2011.2161310
  11. Cameron Browne, Frederic Maire, "Evolutionary Game Design", IEEE Transactions on Computational Intelligence and AI in Games, Vol. 2, No. 1, pp1-16, 2010. https://doi.org/10.1109/TCIAIG.2010.2041928
  12. Edward J. Powley, Simon Colton, Swen Gaudl, Rob Saunders, Mark J. Nelson, "Semi-automated level design via auto-playtesting for handheld casual game creation", IEEE Conference on Computational Intelligence and Games, 2016.
  13. Togelius J., Yannakakis G.N., "Emotion-Driven Level Generation", Emotion in Games. Socio-Affective Computing, vol 4, 2016.
  14. Adam Summerville, Michael Mateas, "Super Mario as a String: Platformer Level Generation Via LSTMs", Neural and Evolutionary Computing (cs.NE), vol 2, 2016.
  15. Unnat Jain, Svetlana Lazebnik, Alexander G. Schwing, "Two Can Play This Game: Visual Dialog With Discriminative Question Generation and Answering", The IEEE Conference on Computer Vision and Pattern Recognition(CVPR), pp5754-5763, 2018.