Human strategy learning-based multi-agent deep reinforcement learning for online team sports game
Open accessAbstract
In 3 vs. 3 online basketball games, finite state machine (FSM)-based Game artificial intelligence (AI) has traditionally been employed. However, limitations such as repetitive behavior patterns and challenges in maintaining systems during redesigns have led to increased research into reinforcement learning-based AI. This shift aims to address the shortcomings of FSM-based approaches. Nevertheless, applying multi-agent reinforcement learning-based AI in commercial online basketball games presents significant challenges, particularly in ensuring real-time processing, which requires efficient methods for managing observational data. In addition, the stochastic nature of action selection in reinforcement learning complicates the accurate learning of behaviors through explicit decision data. Moreover, reinforcement learning, which self-optimizes through exploration and develops its own rules, struggles to mimic human-like behavior patterns that follow predefined strategies in Sports Game. This study introduces a human strategy-based reinforcement learning method designed to address these challenges and replicate human gameplay that adheres to human-defined strategies. The learning of human strategies is enhanced using Ray for the real-time processing of observational data and a multi-phase reward system that distinctly defines rewards based on specific objectives. Furthermore, the proposed method enables real-time, strategy-based action guidance through a Human Strategy AI trained…
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
LLMs such as GPT-4, PaLM, Claude, and LLaMA are pre-trained on massive text corpora using self-supervised objectives and fine-tuned using techniques such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF).
“LLMs such as GPT-4 [81], PaLM [82], Claude https://www.anthropic.com/news/claude-3-5-sonnet, and LLaMA [121] are pre-trained on massive text corpora using self-supervised objectives and fine-tuned using techniques such as Supervised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) [130], [131].”
From AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025) · cites this paper as [131]
Cites
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
Silver, D., Hubert, T., Schrittwieser, J., Antonoglou, I., Lai, M., Guez, A., Lanctot, M., Sifre, L., Kumaran, D., Graepel, T., et al. (2018) · Science · doi:10.1126/science.aar6404 · Cited by 3,562 · see citing works
Policy Invariance Under Reward Transformations: Theory and Application to Reward Shaping
Ng, A. Y., Harada, D., & Russell, S. (1999) · Cited by 1,586 · see citing works
Dota 2 with Large Scale Deep Reinforcement Learning
OpenAI, :, Berner, C., Brockman, G., Chan, B., Cheung, V., Dębiak, P., Dennison, C., Farhi, D., Fischer, Q., et al. (2019) · arXiv · doi:10.48550/arxiv.1912.06680 · Cited by 1,065 · see citing works
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement LearningPreprint
Rashid, T., Samvelyan, M., de Witt, C. S., Farquhar, G., Foerster, J., & Whiteson, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.11485 · Cited by 1,019 · see citing works
(2016) · neural information processing systems · Cited by 735 · see citing works
The StarCraft Multi-Agent Challenge
Samvelyan, M., Rashid, T., Schroeder de Witt, C., Farquhar, G., Nardelli, N., Rudner, T. G. J., Hung, C.-M., Torr, P. H. S., Foerster, J., & Whiteson, S. (2019) · International Joint Conference on Autonomous Agents and Multiagent Systems · doi:10.65109/lvzz5205 · Cited by 453 · see citing works
Emergent Tool Use From Multi-Agent Autocurricula
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., & Mordatch, I. (2019) · arXiv · doi:10.48550/arxiv.1909.07528 · Cited by 424 · see citing works
Welcome to the Era of ChatGPT et al.: The Prospects of Large Language Models
Teubner, T., Flath, C. M., Weinhardt, C., van der Aalst, W., & Hinz, O. (2023) · Business & Information Systems Engineering · doi:10.1007/s12599-023-00795-x · Cited by 384 · see citing works
Teacher–Student Curriculum Learning
Matiisen, T., Oliver, A., Cohen, T., & Schulman, J. (2019) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2019.2934906 · Cited by 351 · see citing works
A Deep Hierarchical Approach to Lifelong Learning in Minecraft
Tessler, C., Givony, S., Zahavy, T., Mankowitz, D. J., & Mannor, S. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10744 · Cited by 300 · see citing works
Emergent Complexity via Multi-Agent CompetitionPreprint
Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., & Mordatch, I. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.03748 · Cited by 266 · see citing works
Automatic Goal Generation for Reinforcement Learning AgentsPreprint
Florensa, C., Held, D., Geng, X., & Abbeel, P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1705.06366 · Cited by 193 · see citing works
StarCraft Micromanagement With Reinforcement Learning and Curriculum Transfer Learning
Shao, K., Zhu, Y., & Zhao, D. (2018) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2018.2823329 · Cited by 175 · see citing works
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep NetworksPreprint
Weinshall, D., Cohen, G., & Amir, D. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1802.03796 · Cited by 172 · see citing works
Reward learning from human preferences and demonstrations in Atari
Ibarz, B., Leike, J., Pohlen, T., Irving, G., Legg, S., & Amodei, D. (2018) · arXiv · doi:10.48550/arxiv.1811.06521 · Cited by 117 · see citing works
Gao, Y., Yuan, X., Yang, D., Hu, Y., Cao, Y., & Schmeink, A. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3367624 · Cited by 86 · see citing works
Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning
Oh, I.-S., Rho, S., Moon, S., Son, S., Lee, H., & Chung, J. (2021) · IEEE Transactions on Games · doi:10.1109/tg.2021.3049539 · Cited by 82 · see citing works
Google Research Football: A Novel Reinforcement Learning Environment
Kurach, K., Raichuk, A., Stańczyk, P., Zając, M., Bachem, O., Espeholt, L., Riquelme, C., Vincent, D., Michalski, M., Bousquet, O., et al. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5878 · Cited by 70 · see citing works
Deep Reinforcement Learning with Interactive Feedback in a Human–Robot Environment
Moreira, I., Rivas, J., Cruz, F., Dazeley, R., Ayala, A., & Fernandes, B. (2020) · Applied Sciences · doi:10.3390/app10165574 · Cited by 51 · see citing works
A Survey of Reinforcement Learning from Human Feedback
Kaufmann, T., Weng, P., Bengs, V., & Hüllermeier, E. (2023) · arXiv · doi:10.48550/arxiv.2312.14925 · Cited by 43 · see citing works
Finite State Machine in Game Development
Jagdale, D. (2021) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-2062 · Cited by 38 · see citing works
Relative Distributed Formation and Obstacle Avoidance with Multi-agent Reinforcement Learning
Yan, Y., Li, X., Qiu, X., Qiu, J., Wang, J., Wang, Y., & Shen, Y. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9812263 · Cited by 36 · see citing works
Peng, G., Yang, J., Li, X., & Khyam, M. O. (2022) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2022.3228901 · Cited by 35 · see citing works
Curriculum-Based Asymmetric Multi-Task Reinforcement Learning
Huang, H., Ye, D., Shen, L., & Liu, W. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3223872 · Cited by 24 · see citing works
Collaborative hunting in artificial agents with deep reinforcement learning
Tsutsui, K., Tanaka, R., Takeda, K., & Fujii, K. (2024) · eLife · doi:10.7554/elife.85694 · Cited by 19 · see citing works
Wang, J., Fox, I., Skaza, J., Linck, N., Singh, S. P., & Wiens, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1803.02940 · Cited by 18 · see citing works
Hossain, S., & Lee, D. J. (2019) · The Journal of Korea Robotics Society · doi:10.7746/jkros.2019.14.2.122 · Cited by 16 · see citing works
Gao, Y., Wang, S., Liu, M., & Hu, Y. (2023) · IEEE/CIC International Conference on Communications in China (ICCC) · doi:10.1109/iccc57788.2023.10233375 · Cited by 16 · see citing works
Jia, H., Hu, Y., Chen, Y., Ren, C., Lv, T., Fan, C., & Zhang, C. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.03204 · Cited by 15 · see citing works
An Artificial Intelligence Evaluation on FSM-Based Game NPC
Lee, M. (2014) · Journal of Korea Game Society · doi:10.7583/jkgs.2014.14.5.127 · Cited by 11 · see citing works
Hierarchical Reinforcement Learning: Assignment of Behaviours to Subpolicies by Self-Organization
Moerman, W. (2009) · Cited by 10 · see citing works
Generating Automatic Curricula via Self-Supervised Active Domain RandomizationPreprint
Raparthy, S. C., Mehta, B., Golemo, F., & Paull, L. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2002.07911 · Cited by 6 · see citing works
Choi, T., Cho, K., & Sung, Y. (2023) · Mathematics · doi:10.3390/math11051110 · Cited by 5 · see citing works
Self-citation
Flagged first, then by citations
1 of the 34 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
AI Agents vs. Agentic AI: A Conceptual taxonomy, applications and challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2026) · Information Fusion · doi:10.1016/j.inffus.2025.103599 · Cited by 244 · see citing works
“LLMs such as GPT-4 [79], PaLM [80], Claude Claude 3.5 Sonnet, and LLaMA [119] are pre-trained on massive text corpora using self-supervised objectives and fine-tuned using techniques such as Super-vised Fine-Tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF) [128,129].”
InfluentialAI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
Sapkota, R., Roumeliotis, K. I., & Karkee, M. (2025) · SuperIntelligence - Robotics - Safety & Alignment · doi:10.70777/si.v2i3.15161 · Cited by 186 · see citing works
AI‐Driven Soccer Training Optimization Method via Space‐Air‐Ground Integrated Network
Liu, D., Li, D., & Wang, Q. (2025) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70318 · Cited by 2 · see citing works
Optimizing Competitive Sports Training Strategies with Adaptive Deep Reinforcement Learning
Li, K. (2025) · International Conference on Intelligent Computing and Robotics (ICICR) · doi:10.1109/icicr65456.2025.00060
Application of Attention-Based Multi-Agent Deep Reinforcement Learning in Team Sports Collaboration
Fan, S., & Chen, X. (2025) · International Conference on Artificial Intelligence and Digital Ethics (ICAIDE) · doi:10.1109/icaide65466.2025.11189420
Enhancing Entertainment Through Reinforcement Learning: Applications in Gaming
Mustapha, A. A., Yoosuf, M. S., Selvarajan, S., Khadidos, A., & Khadidos, A. O. (2026) · International Journal of Computer Games Technology · doi:10.1155/ijcg/3031640
Guo, Q., & Zhang, J. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-25609-6_26
Artificial Intelligence in an Online Multiplayer Game: A Systematic Literature Review
Perdana, Y. R., & Karsen, M. (2026) · International Conference on ICT for Smart Society (ICISS) · doi:10.1109/iciss71466.2026.11715201
- Authors
- Lee, S., Lee, G., Kim, W., Kim, J., Park, J., & Cho, K.
- Affiliations
- Dongguk University (KR)
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 15437-15452
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4406610611
- Cited by
- 7
- References
- 34
- Citations by year
- 2026: 3 · 2025: 4
- FWCI
- 2.82
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Ministry of Science and ICT, South Korea (IITP-2024-RS-2023-00254592)
- Ministry of Culture, Sports and Tourism (R2022020003)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence Applications
- Keywords
- multi-agent deep reinforcement learning, game AI, rays
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
