Generative Methods for Creating Adaptive Playable Characters in Service Games
https://doi.org/10.26907/1562-5419-2025-28-3-468-483
Abstract
With the growing popularity of game services that require constant content updates to retain players, automating the generation of adaptive playable characters has become an urgent task. This article examines existing approaches to character generation, including evolutionary algorithms, and in-session adaptation systems. Current solutions are limited by their inability to provide sufficient long-term adaptation to individual player styles and their reliance on manual design.
To address these limitations, we propose a three-component system that integrates: player action modeling based on gameplay replays using reinforcement learning (RL) agents, character generation through combinatorial mechanics and parameter balancing, automatic validation via simulations to assess balance and alignment with a player’s individual style.
This work synthesizes contemporary research, highlighting the potential of generative methods to reduce development costs for game services. The results could accelerate prototyping and enhance the long-term viability of live-service projects.
About the Author
Timur Ruzelevich Arslanov
Kazan (Volga region) Federal University
Russian Federation
Russian Federation
References
1. Rousseau J. Report: 95% of studios are working on or aim to release a live service game // GamesIndustry.biz. 2024. URL: https://www.gamesindustry.biz/report-95-of-studios-are-working-on-or-aim-to-release-a-live-service-game.
2. Game Development Report / Rendered Venture Capital, Griffin Gaming Partners. 2024. URL: https://griffingp.com/2023-game-development-research/.
3. Canheti C, Andalo F., Vieira M.L.H. Case Study: Game Character Creation Process // Advances in Human Factors in Wearable Technologies and Game Design: Advances in Intelligent Systems and Computing / T.Z. Ahram (Ed.). Cham: Springer International Publishing, 2019. Vol. 795. P. 343–354. https://doi.org/10.1007/978-3-319-94619-1_34.
4. Shubin A.V., Kugurakova V.V. Designing a tool for creating gameplay through the systematization of game mechanics // Russian Digital Libraries Journal. Vol. 27, No. 5. P. 774–795. https://doi.org/10.26907/1562-5419-2024-27-5-774-795. https://doi.org/10.26907/1562-5419-2024-27-5-774-795.
5. Browne C, Maire F. Evolutionary Game Design // IEEE Transactions on Computational Intelligence and AI in Games. 2010. Vol. 2, No. 1. P. 1–16. https://doi.org/10.1109/TCIAIG.2010.2041928.
6. Cannizzo A., Ramírez E. Towards Procedural Map and Character Generation for the MOBA Game Genre // Ingeniería y Ciencia. 2015. Vol. 11, No. 22. P. 95–119. https://doi.org/10.17230/ingciencia.11.22.5.
7. Pantaleev A. In Search of Patterns: Disrupting RPG Classes through Procedural Content Generation // Proceedings of the third workshop on Procedural Content Generation in Games FDG’12: International Conference on the Foundations of Digital Games. 2012. P. 1–5. https://doi.org/10.1145/2538528.2538532
8. Skjærseth E.H., Vinje H. Evolutionary algorithms for generating interesting fighting game character mechanics: Master thesis. Trondheim: Norwegian University of Science and Technology, 2020. URL: https://hdl.handle.net/11250/2777860.
9. No H.-S., Rhee D.-W. A Study on The Game Character Creation Using Genetic Algorithm in Football Simulation Games // Journal of Korea Game Society. 2017. Vol. 17, No. 6. P. 129–137. https://doi.org/10.7583/JKGS.2017.17.6.129.
10. Pan C.-F, Min X.-Y. et al. Behavior imitation of individual board game players // Applied Intelligence. 2023. Vol. 53, No. 10. P. 11571–11585. https://doi.org/10.1007/s10489-022-04050-w.
11. Partla N. et al. Player Imitation for Build Actions in a Real-Time Strategy Game // AIIDE workshop on Artificial Intelligence for Strategy Games. 2019.
12. Kozik A., Machalewski T. et al. Mimicking Playstyle by Adapting Parameterized Behavior Trees in RTS Games / arXiv:2111.12144 [cs]. 2021. URL: http://arxiv.org/abs/2111.12144.
13. Liu S., Chaoran L. et al. Automatic generation of tower defense levels using PCG // Proceedings of the 14th International Conference on the Foundations of Digital Games FDG’19: The Fourteenth International Conference on the Foundations of Digital Games. San Luis Obispo California USA: ACM, 2019. P. 1–9. https://doi.org/10.1145/3337722.3337723
14. Chen L., Lu K et al. Decision Transformer: Reinforcement Learning via Sequence Modeling. Decision Transformer / arXiv:2106.01345 [cs]. 2021. URL: http://arxiv.org/abs/2106.01345.
15. Kugurakova V.V. A formal approach to spatio-temporal modeling of game systems // Uchenye Zapiski Kazanskogo Universiteta. Seriya Fiziko-Matematicheskie Nauki. 2024. Vol. 166, No. 4. P. 532–554. https://doi.org/10.26907/2541-7746.2024.4.532-554.
Review
For citations:
Arslanov T.R. Generative Methods for Creating Adaptive Playable Characters in Service Games. Russian Digital Libraries Journal. 2025;28(3):468-483. (In Russ.) https://doi.org/10.26907/1562-5419-2025-28-3-468-483
Views:
126
JATS XML
Email this article 