Multi-agent reinforcement learning on GRF cthard 4v3
0.89RewardFULLOBS
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FULLOBSAlgorithm=MAPPO2026.06 | 0.89 | 382 | |
| HICOMMAlgorithm=MAPPO2026.06 | 0.86 | 14 | |
| T2MACAlgorithm=MAPPO2026.06 | 0.85 | 137 | |
| CACOMAlgorithm=MAPPO2026.06 | 0.83 | 21.4 | |
| FULLOBSAlgorithm=IPPO2026.06 | 0.79 | 351 | |
| PARTIALOBSAlgorithm=MAPPO2026.06 | 0.79 | 0 | |
| HICOMMAlgorithm=IPPO2026.06 | 0.76 | 13.6 | |
| CACOMAlgorithm=IPPO2026.06 | 0.73 | 16.5 | |
| T2MACAlgorithm=IPPO2026.06 | 0.73 | 192 | |
| PARTIALOBSAlgorithm=IPPO2026.06 | 0.7 | 0 |