Metraipolis › archive › dc_9fbef83ef5de

SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation — arXiv:2608.26683

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.26683
License (as archived): CC0-1.0
Archived: 2026-10-17T13:16:40.723Z
SHA-256 of the archived text: ccff6f041fc88d4565882bcadc3bf7f6ed7745cd77a5fc1021c7507e6ea31c04
Stable URL of this page: https://metraipolis.com/documento/dc_9fbef83ef5de

How to cite

SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation — arXiv:2608.26683 — arXiv (en), https://arxiv.org/abs/2608.26683 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9fbef83ef5de (Metraipolis archive dc_9fbef83ef5de, sha256 ccff6f041fc88d4565882bcadc3bf7f6ed7745cd77a5fc1021c7507e6ea31c04)

BibTeX

@misc{dc9fbef83ef5de,
  title = {SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation — arXiv:2608.26683},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26683},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9fbef83ef5de; sha256 ccff6f041fc88d4565882bcadc3bf7f6ed7745cd77a5fc1021c7507e6ea31c04},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26683. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Cooperative multi-agent reinforcement learning (MARL) faces significant challenges in maintaining robust coordination under noisy observations. Although observation disturbances are often introduced independently across agents, their downstream effects on cooperative decision-making can become structured through underlying cooperation structures. We characterize this phenomenon as structured noise effects, where noise-induced decision effects exhibit local correlation among agents with stronger task-related dependencies while remaining globally heterogeneous across different agents and local structures. Existing robust MARL methods, however, rarely explicitly characterize or exploit such structure-dependent noise effects. To address this limitation, we propose SIGMA, a hierarchical collaboration framework that exploits cooperation structures to learn robust representations under noisy observations. SIGMA first organizes agents into adaptive local structures through density-based grouping and performs intra-group consensus aggregation to preserve shared task-relevant information while smoothing agent-specific representation deviations. Inter-group attention then adaptively integrates information across different groups to preserve global coordination while accommodating their heterogeneous contributions. Experiments on noisy-observation tasks in StarCraft II empirically validate the structured noise effects and demonstrate that SIGMA consistently improves robustness under observation noise while maintaining competitive performance in noise-free environments.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.MA).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2608.26683 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T13:16:17.002Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).