SOURCE-LINKED INTELLIGENCE

SIGMA: Structured Noise-Effect-Aware Grouped Multi-Agent Aggregation

arXiv · AI, language, vision and robotics · article · Aug 27, 2026 · UTC

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 s

Read original source ↗ Open in workspace

recordType

paper

region

Global