Multi-Agent Reinforcement Learning on SMAC terran_5v5 v2 (test)
17.9RewardFULLOBS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FULLOBSAlgorithm=QMIX2026.06 | 17.9 | 152.5 | |
| HiCommAlgorithm=QMIX2026.06 | 17.6 | 8.4 | |
| PARTIALOBSAlgorithm=QMIX2026.06 | 16 | 0 | |
| CACOMAlgorithm=QMIX2026.06 | 16 | 28.3 | |
| T2MACAlgorithm=QMIX2026.06 | 15.6 | 142.8 |