EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning

Yirui Liu, Xueqiang Gu, Caiming Zheng, Xin Xu, Zhangling Wang, Wanpeng Zhang, Yixing Lan

CAAI Transactions on Intelligence Technology · 2026-10 · 11 (5) · 1496-1510

DOI: 10.1049/cit2.70127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CAAI Transactions on Intelligence Technology, online erschienen am 09.04.2026. Verfasst von Yirui Liu und 6 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Policy heterogeneity is crucial for achieving sophisticated coordination in complex collaborative tasks, which has emerged as one of the key challenges in multi‐agent reinforcement learning (MARL) in recent years. Notably, the grouping paradigm has made remarkable progress in addressing policy heterogeneity. However, most existing grouping methods require predefining the number of groups or the composition and quantity of members within each group, which need to be individually configured for each scenario and are difficult to set without sufficient expert knowledge. By contrast, we propose a novel MARL grouping algorithm named Credit‐driven adaptive Grouping (CreateG) which divides the entire training process into multiple phases and reallocates poorly adapted (low‐credit) individuals at each training stage. With the help of the mechanism we designed, an environment‐adaptive grouping is ultimately formed. Furthermore, we design a hierarchical hypernetwork architecture to accommodate this adaptive grouping mechanism. Experiments conducted on StarCraft II micromanagement hard and superhard tasks, Google Research Football and TAG scenarios show CreateG achives state‐of‐the‐art MARL performance. Moreover, extensive ablation studies elucidate the operational mechanism of the grouping strategy and other components demonstrate how they enhance overall performance.

Zitieren

APA

Liu, Y., Gu, X., Zheng, C., Xu, X., Wang, Z., Zhang, W., & Lan, Y. (2026). Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning. CAAI Transactions on Intelligence Technology, 11(5), 1496-1510. https://doi.org/10.1049/cit2.70127

Vancouver

Liu Y, Gu X, Zheng C, Xu X, Wang Z, Zhang W, et al. Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning. CAAI Transactions on Intelligence Technology. 2026;11(5):1496-1510. doi:10.1049/cit2.70127

BibTeX
@article{Liu2026,
  author = {Liu, Yirui and Gu, Xueqiang and Zheng, Caiming and Xu, Xin and Wang, Zhangling and Zhang, Wanpeng and Lan, Yixing},
  title = {Credit‐Driven Adaptive Grouping for Refined Cooperative Multi‐Agent Reinforcement Learning},
  journal = {CAAI Transactions on Intelligence Technology},
  year = {2026},
  volume = {11},
  number = {5},
  pages = {1496--1510},
  doi = {10.1049/cit2.70127}
}
Kostenlos starten →