Multi-agent Reinforcement Learning on SMAC protoss_5v5 v2 (test)
17.8RewardFULLOBS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FULLOBSAlgorithm=QMIX2026.06 | 17.8 | 193.8 | |
| HiCommAlgorithm=QMIX2026.06 | 17.4 | 10.3 | |
| PARTIALOBSAlgorithm=QMIX2026.06 | 16.3 | 0 | |
| CACOMAlgorithm=QMIX2026.06 | 14.5 | 39.1 | |
| T2MACAlgorithm=QMIX2026.06 | 14.1 | 185.1 |