Multi-agent Reinforcement Learning on SMAC zerg_5v5 v2 (test)
14.9RewardFULLOBS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FULLOBSAlgorithm=QMIX2026.06 | 14.9 | 95.2 | |
| HiCommAlgorithm=QMIX2026.06 | 13.9 | 5.4 | |
| CACOMAlgorithm=QMIX2026.06 | 12.5 | 15.9 | |
| PARTIALOBSAlgorithm=QMIX2026.06 | 12.3 | 0 | |
| T2MACAlgorithm=QMIX2026.06 | 12.3 | 85.5 |