EUVIMEDEUVIMED entdecken
Crossref

Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning

Zhuhui Li, Chunbo Luo, Liming Huang, Luyu Qi, Geyong Min

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29538-29545

DOI: 10.1609/aaai.v40i35.40196 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zhuhui Li und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-agent multi-objective systems (MAMOS) have emerged as powerful frameworks for modelling complex decision-making problems across various real-world domains, such as robotic exploration, autonomous traffic management, and sensor network optimisation. MAMOS enhances scalability and robustness through decentralised control and more accurately captures inherent trade-offs between conflicting objectives. In MAMOS, each agent uses utility functions that map return vectors to scalar values. Existing MAMOS optimisation methods face significant challenges in handling heterogeneous objective and utility function settings, where training non-stationarity is intensified due to private utility functions and the associated policies. In this paper, we first theoretically prove that direct access to, or structured modeling of, global utility functions is necessary to achieve the Bayesian Nash Equilibrium under decentralised execution constraints. To access the global utility functions while preserving the decentralised execution, we propose an Agent-Attention Multi-Agent Multi-Objective Reinforcement Learning (AA-MAMORL) framework. Our approach implicitly learns a joint belief over other agents’ utility functions and their associated policies during centralised training, effectively mapping global states and utilities to each agent's policy. During execution, each agent independently selects actions based on local observations and its private utility function to approximate a BNE, without relying on inter-agent communication. We evaluate our framework through extensive experiments in a custom-designed MAMO Particle environment and the standard MOMALand benchmark. The results demonstrate that accessibility to global preferences and our proposed AA-MAMORL significantly improves performance and consistently outperforms state-of-the-art methods.

Zitieren

APA

Li, Z., Luo, C., Huang, L., Qi, L., & Min, G. (2026). Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29538-29545. https://doi.org/10.1609/aaai.v40i35.40196

Vancouver

Li Z, Luo C, Huang L, Qi L, Min G. Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29538-29545. doi:10.1609/aaai.v40i35.40196

BibTeX
@article{Li2026,
  author = {Li, Zhuhui and Luo, Chunbo and Huang, Liming and Qi, Luyu and Min, Geyong},
  title = {Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29538--29545},
  doi = {10.1609/aaai.v40i35.40196}
}
Kostenlos starten →