BALANCING MECHANISM IN STELLAR 4X GAMES USING GRAPHSAGE-BASED INDUCTIVE REPRESENTATION LEARNING
Keywords:
Graph Neural Networks, Graphsage, Stellar 4X Game, Game Balance, Inductive Learning, Node ClassificationAbstract
Balancing a computer game can be a challenging and complex task. Achieving a perfect balance can be difficult, as there is no universal way to determine game balance, and no mathematical formula can be applied to all games in a given genre. The map used in stellar 4X games can be represented as a graph. The distribution of planets the player encounters during the game impacts the balance. This study aims to apply a balancing mechanism using inductive machine learning techniques based on GraphSAGE. The GraphSAGE model achieved a performance rate of 94% in the planet classification task based on the game map structure and game progress. Tests of the map-balancing method were conducted on an experimental stellar 4X game that was prepared for the study. The game's mechanics are examined and a cost-benefit analysis of the available decisions is performed during the game. For the examinations, an algorithm simulating a player's behavior is implemented, which executes variants of the strategies available in the game. Trials were performed on automated skirmishes. The results indicated the potential of the GraphSAGE-based inductive representation learning model to improve gameplay balance in 4X stellar games. The outcome of balance improvement was influenced through the use of an adequately prepared input data set for the learning process.
References
Schreiber, I.; Romero, B. Definition of game balance. In Game Balance; CRC Press: Boca Raton, FL, USA, 2022; pp. 344–359.
Leigh, R.; Schonfeld, J.; Louis, S.J. Using Coevolution to Understand and Validate Game Balance in Continuous Games. In Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation, Atlanta, GA, USA, 12–16 July 2008; pp. 1563–1570.
Juego Studios. Why Game Balancing is crucial in Game Development. Available online: https://juegostudio.com/blog/why–game–balancing–crucial–game–development (accessed on 16 December 2023).
Shell, J. Impact of balance on gameplay. In The Art of Game Design: A Book of Lenses, 3rd ed.; CRC Press: Boca Raton, FL, USA, 2020; pp. 168–210.
Becker, A.; Görlich, D. What is Game Balancing? – An Examination of Concepts. paradigmplus 2020, 1, 22–41.
Lara-Cabrera, R.; Cotta, C.; Fernández-Leiva, A. J. On balance and dynamism in procedural content generation with self-adaptive evolutionary algorithms. Nat. Comput. 2014, 13, 157–168.
Mahlmann, T.; Togelius, J.; Yannakakis, G. N. Evolving card sets towards balancing dominion. In Proceedings of the 2012 IEEE Congress on Evolutionary Computation, Brisbane, Australia, 10–15 June 2012; pp. 1–8.
Lanzi, P. L.; Loiacono, D.; Stucchi, R. Evolving maps for match balancing in first person shooters. In Proceedings of the 2014 IEEE Conference on Computational Intelligence and Games, Dortmund, Germany, 26–29 August 2014; pp. 1–8.
Pfau, J.; Liapis, A.; Volkmar, G.; Yannakakis, G. N.; Malaka, R. Dungeons & Replicants: Automated Game Balancing via Deep Player Behavior Modeling. In Proceedings of the 2020 IEEE Conference on Games (CoG), Osaka, Japan, 24–27 August 2020; pp. 431–438.
Awiszus, M.; Schubert, F.; Rosenhahn, B. TOAD-GAN: Coherent Style Level Generation from a Single Example. arXiv 2020, arXiv:2008.01531.
Gisslén, L.; Eakins, A.; Gordillo, C.; Bergdahl, J.; Tollmar, K. Adversarial Reinforcement Learning for Procedural Content Generation. In Proceedings of the 2021 IEEE Conference on Games (CoG), Copenhagen, Denmark, 17–20 August 2021; pp. 1–8.
Huber, T.; Mertes, S.; Rangelova, S.; Flutura, S.; André, E. Dynamic Difficulty Adjustment in Virtual Reality Exergames through Experience–driven Procedural Content Generation. arXiv 2021, arXiv:2108.08762.
Liu, J.; Snodgrass, S.; Khalifa, A.; Risi, S.; Yannakakis, G. N.; Togelius, J. Deep learning for procedural content generation. Neural. Comput. & Applic. 2021, 30, 19–37.
Shaker, N.; Togelius, J.; Nelson, M. J. In Procedural Content Generation in Games, 1st ed.; Springer International Publishing: Cham, Switzerland, 2016.
Togelius, J.; Yannakakis, G. N.; Stanley, K. O.; Browne, C. Search-Based Procedural Content Generation: A Taxonomy and Survey. IEEE Transactions on Computational Intelligence and AI in Games 2011, 3, 172–186.
Togelius, J.; Preuss, M.; Beume, N.; Wessing, S.; Hagelbäck, J. et al. Controllable procedural map generation via multiobjective evolution. Gen. Progr. & Evol. Mach. 2013, 14, 245–277.
Karavolos, D.; Liapis, A.; Yannakakis, G. N. Using a Surrogate Model of Game– play for Automated Level Design. In Proceedings of the 2018 IEEE Conference on Computational Intelligence and Games (CIG), Maastricht, Netherlands, 14–17 August 2018; pp. 1–8.
Olesen, J. K.; Yannakakis, G. N.; Hallam, J. Real-time challenge balance in an RTS game using rtNEAT. In Proceedings of the 4th IEEE Symposium on Computational Intelligence and Games, Perth, Australia, 15–18 December 2008; pp. 87–94.
Stephens, C.; Exton, C. Balancing Multiplayer Games across Player Skill Levels using Deep Reinforcement Learning. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence (ICAART), Online, 3–5 February 2022; pp. 827–833.
Rupp, F.; Eberhardinger, M.; Eckert, K. Balancing of competitive two–player Game Levels with Reinforcement Learning. arXiv 2023, arXiv:2306.04429.
Kotaku. What’s A 4X Game And Why Do They Rule? Available online: https://kotaku.com.au/2021/10/whats-a-4x-game-andwhy-do-they-rule (accessed on 10 December 2023).
Hetfeld, M. The best 4X games that embody the classic genre. Available online: https://www.gamesradar.com/best-4x-games (accessed on 15 December 2023).
DiamondLobby. What is a 4X Game? Available online: https://diamondlobby.com/what-is-a-4x-game (accessed on 17 January 2024).
MobyGames. 4X: Definition. Available online: https://mobygames.com/genre/sheet/4x (accessed on 17 January 2024).
Paradox Interactive. Stellaris. Available online: https://paradoxinteractive.com/stellaris (accessed on 10 December 2023).
Wargaming Labs. Master of Orion. Available online: https://masteroforion.eu/intro (accessed on 10 December 2023).
Yu, B.; Yin, H.; Zhu, Z. Spatio–temporal graph convolutional networks: A deep learning framework for traffic forecasting. arXiv 2017, arXiv:1709.04875.
Monti, F.; Boscaini, D.; Masci, J.; Rodolà, E.; Svoboda, J.; Bronstein M. Geometric deep learning on graphs and manifolds using mixture model CNNs. arXiv 2016, arXiv:1611.08402.
Yao, L.; Mao, C.; Luo, Y. Graph Convolutional Networks for Text Classification. arXiv 2019, arXiv:1809.05679.
Qiu, J.; Tang, J.; Ma, H.; Dong, Y.; Wang, K.; Tang, J. Deepinf: Social influence prediction with deep learning. arXiv 2018, arXiv:1807.05560.
Duvenaud, D.; Maclaurin, D.; Iparraguirre, J.; Bombarell, R.; Hirzel, T.; Aspuru-Guzik, A.; Adams, R. Convolutional networks on graphs for learning molecular fingerprints. arXiv 2015, arXiv:1509.09292.
Bruna, J.; Zaremba, W.; Szlam, A.; LeCun, Y. Spectral networks and locally connected networks on graphs. arXiv 2013, arXiv:1312.6203.
Zhang, S.; Tong, H.; Xu, J.; Maciejewski, R. Graph convolutional networks: a comprehensive review. Comp. Soc. Net. 2019, 6, 11–23.
Kipf, T. N.; Welling, M. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907.
Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; Yu, P. A Comprehensive Survey on Graph Neural Networks. arXiv 2019, arXiv:1901.00596.
Perozzi, B.; Al-Rfou, R.; Skiena, S. Deepwalk: Online learning of social representations. arXiv 2014, arXiv:1403.6652.
Grover, A.; Leskovec, J. node2vec: Scalable feature learning for networks. arXiv 2016, arXiv:1607.00653.
Zhou, J.; Cui, G.; Hu, S.; Zhang, Z.; Yang, C.; Liu, Z.; Wang, L.; Li, C.; Sun, M. Graph Neural Networks: A Review of Methods and Applications. arXiv 2020, arXiv:1812.08434.
Zhang, S.; Tong, H.; Xu, J.; Maciejewski R. Graph Convolutional Networks: Algorithms, Applications and Open Challenges. In Proceedings of the Computational Data and Social Networks - 7th International Conference, CSoNet 2018, Shanghai, China, 18–20 December 2018; pp. 79–91.
Hamilton, W.; Ying, Z.; Leskovec, J. Inductive representation learning on large graphs. arXiv 2017, arXiv:1312.6203.
Gilbert, E. N. Random Graphs. An. Math. Stat. 1959, 30, 1141–1144.
Dantzig G.; Fulkerson D. R. On the Max–Flow Min–Cut Theorem of Networks. Lin. Ineq., Ann. Math. Studies 1957, 38, 215.
Van der Maaten, L.; Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 2008, 9, 2579–2605.
Downloads
Published
Issue
Section
License
Copyright (c) 2024 Sebastian Piotr Dabrowski (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
