Multi-agent reinforcement learning on CC4
2,110RewardFULLOBS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FULLOBSAlgorithm=MAPPO2026.06 | 2,110 | 8,420.6 | |
| HICOMMAlgorithm=MAPPO2026.06 | 1,941 | 7.7 | |
| FULLOBSAlgorithm=IPPO2026.06 | 1,763 | 8,420.6 | |
| CACOMAlgorithm=MAPPO2026.06 | 1,692 | 36.8 | |
| T2MACAlgorithm=IPPO2026.06 | 1,623 | 143.8 | |
| T2MACAlgorithm=MAPPO2026.06 | 1,554 | 134.2 | |
| HICOMMAlgorithm=IPPO2026.06 | 1,527 | 8.4 | |
| CACOMAlgorithm=IPPO2026.06 | 1,517 | 41.3 | |
| PARTIALOBSAlgorithm=IPPO2026.06 | 1,436 | 0 | |
| PARTIALOBSAlgorithm=MAPPO2026.06 | 990 | 0 |