SACHI uses graph transformer convolutions on inter-agent coordination graphs to enrich partial-observation agents with content-dependent teammate information, yielding statistically significant gains over baselines in five cooperative tasks.
Masked label prediction: Unified message passing model for semi-supervised classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning
SACHI uses graph transformer convolutions on inter-agent coordination graphs to enrich partial-observation agents with content-dependent teammate information, yielding statistically significant gains over baselines in five cooperative tasks.