List your company

Multi-Agent Reinforcement Learning on SMAC 3s5z v1 (test)

92.7Win RateMAGI
85.21287.15689.191.044Dec 11, 2025Jan 6, 2026Feb 1, 2026Feb 27, 2026Mar 25, 2026Apr 20, 2026May 17, 2026

Evaluation results

MethodLinks
MAGIUnit Composition=2-type, Training Budget=1.2M2026.0592.7—
AIB-onlyUnit Composition=2-type, Training Budget=1.2M2026.0592.6—
HIBCGUnit Composition=2-type, Training Budget=1.2M2026.0592.6—
BVMEBandwidth Ratio (r)=0.05, Message Reduction vs 0.30=83.3%2025.1291.560.5517
CommFormerUnit Composition=2-type, Training Budget=1.2M2026.0591.2—
HIB-flatUnit Composition=2-type, Training Budget=1.2M2026.0590.8—
QMIXUnit Composition=2-type, Training Budget=1.2M2026.0589.7—
GACGUnit Composition=2-type, Training Budget=1.2M2026.0589.7—
BVMEUnit Composition=2-type, Training Budget=1.2M2026.0589.6—
BVMEBandwidth Ratio (r)=0.075, Message Reduction vs 0.30=75.0%2025.1287.290.5427
GACGBandwidth Ratio (r)=0.32025.1286.770.5201
BVMEBandwidth Ratio (r)=0.1, Message Reduction vs 0.30=66.7%2025.1286.770.557
ExpoCommUnit Composition=2-type, Training Budget=1.2M2026.0585.5—