Scaling Up Cooperative Multi-Agent Reinforcement Learning Through Hierarchical Heterogeneous Modular Architectures
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41048-41049
DOI: 10.1609/aaai.v40i48.42150 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Minghong Geng.
Abstract (Originalsprache)
Multi-agent reinforcement learning enables sophisticated collaborative behaviors in autonomous systems, yet fundamental scalability barriers persist: existing methods struggle to coordinate large agent populations and face challenges with extended decision-making horizons. This research develops hierarchical approaches to scale up multi-agent learning systems through two complementary directions: structural scaling for coordinating increasing numbers of agents and temporal scaling for extending decision-making horizons. This paper presents four integrated contributions: a taxonomic survey establishing hierarchical architectures as the theoretical foundation for scalable multi-agent learning systems, a benchmark for long-horizon multi-objective multi-agent reinforcement learning, a framework integrating self-organizing neural networks with multiple reinforcement learning agents for hierarchical tri-level control, and a framework leveraging large language models for zero-shot multi-agent planning. Through comprehensive validation, this work demonstrates that hierarchical, heterogeneous, modular architectures provide unified, interpretable solutions to multi-agent scalability, bridging theoretical multi-agent reinforcement learning research with real-world deployment requirements.
Zitieren
APA
Geng, M. (2026). Scaling Up Cooperative Multi-Agent Reinforcement Learning Through Hierarchical Heterogeneous Modular Architectures. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41048-41049. https://doi.org/10.1609/aaai.v40i48.42150
Vancouver
Geng M. Scaling Up Cooperative Multi-Agent Reinforcement Learning Through Hierarchical Heterogeneous Modular Architectures. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41048-41049. doi:10.1609/aaai.v40i48.42150
BibTeX
@article{Geng2026,
author = {Geng, Minghong},
title = {Scaling Up Cooperative Multi-Agent Reinforcement Learning Through Hierarchical Heterogeneous Modular Architectures},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41048--41049},
doi = {10.1609/aaai.v40i48.42150}
}
EUVIMED