Integrasi Deep Reinforcement Learning untuk Pengendalian Musuh yang Dinamis pada Game Action RPG
DOI:
https://doi.org/10.29407/19tm0m83Abstract
Perilaku musuh dalam game sering kali dibangun menggunakan pola statis yang sulit beradaptasi dengan pemain, sehingga menurunkan tantangan dan daya tarik permainan. Penelitian ini mengembangkan sistem kecerdasan buatan (AI) musuh pada game 3D menggunakan pendekatan Deep Reinforcement Learning (DRL) yang terintegrasi dengan Godot Engine. Sistem ini memungkinkan musuh mengambil keputusan secara adaptif berdasarkan situasi permainan. Jika sistem DRL tidak tersedia, musuh tetap dapat beraksi menggunakan logika konvensional yang telah diprogram. Evaluasi menunjukkan bahwa musuh berbasis DRL memperoleh cumulative reward lebih tinggi dan perilaku yang lebih variatif dibandingkan AI berbasis aturan tetap.
Keywords:
Deep Reinforcement Learning, Kecerdasan Buatan, Permainan Aksi##plugins.themes.default.displayStats.downloads##
References
[1] P. Almeida, V. Carvalho, dan A. Simões, "Reinforcement Learning Applied to AI Bots in First-Person Shooters: A Systematic Review," Algorithms, vol. 16, no. 7, p. 323, 2023. doi: 10.3390/a16070323.
[2] M. Ranaweera and Q. H. Mahmoud, “Deep Reinforcement Learning with Godot Game Engine,” Electronics, vol. 13, no. 5, p. 985, 2024, doi: 10.3390/electronics13050985.
[3] E. Beeching, J. Dibangoye, O. Simonin, and C. Wolf, “Godot Reinforcement Learning Agents,” arXiv preprint, arXiv:2112.03636, 2021, doi: 10.48550/arXiv.2112.03636.
[4] J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal Policy Optimization Algorithms,” arXiv preprint, arXiv:1707.06347, 2017, doi: 10.48550/arXiv.1707.06347.
[5] H. Kim, "An Efficient Load Balancing Scheme for Gaming Server Using Proximal Policy Optimization Algorithm," Journal of Information Processing Systems, vol. 17, no. 2, pp. 297-305, 2021. DOI: 10.3745/JIPS.03.0158.
[6] A. Juliani et al., “Unity: A General Platform for Intelligent Agents,” arXiv preprint, arXiv:1809.02627, 2018, doi: 10.48550/arXiv.1809.02627.
[7] L. Wang, B. Li, S. Wang, dan T. Wang, "Enhanced Proximal Policy Optimization for Complex Game AI: Applying Reinforcement Learning to Super Mario," Academic Journal of Computing & Information Science, vol. 7, no. 11, pp. 150–154, 2024. doi: 10.25236/AJCIS.2024.071120.
[8] Z. Yang, C. Li, X. Wang, dan Y. Tian, "PPO-ACT: Proximal Policy Optimization with Adversarial Curriculum Transfer for Spatial Public Goods Games," arXiv preprint arXiv:2505.04302, 2025. doi: 10.48550/arXiv.2505.04302.
[9] S. Corecco, G. Adorni, dan L. M. Gambardella, "Proximal Policy Optimization-Based Reinforcement Learning and Hybrid Approaches to Explore the Cross Array Task Optimal Solution," Machine Learning and Knowledge Extraction, vol. 5, no. 4, pp. 1660–1679, 2023. doi: 10.3390/make5040082.
[10] F. Martinez-Lopez, J. Chen, dan Y. Lu, "SPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics," arXiv preprint arXiv:2502.14264, 2025. doi: 10.48550/arXiv.2502.14264.
[11] Y. K. Purwanto dan D.-K. Kang, "Multi-Agent Deep Reinforcement Learning for Fighting Game: A Comparative Study of PPO and A2C," International Journal of Internet, Broadcasting and Communication, vol. 16, no. 3, pp. 192–198, 2024. doi: 10.7236/IJIBC.2024.16.3.192
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Muhammad Ainul Yaqin, Danang Wahyu Widodo, Ardi Sanjaya
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
