| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TREA rdist | MADDPG | Mean Episodic Reward32,421 | 42 | 4d ago | |
| REF rac-dist | DRE-MARL | Mean Episodic Reward6,340 | 21 | 4d ago | |
| CN rac-dist | DRE-MARL | Mean Episodic Reward888 | 21 | 4d ago | |
| REF rdist | MADDPG | Mean Episodic Reward-43 | 21 | 4d ago | |
| CN rdist | DRE-MARL | Mean Episodic Reward-161 | 21 | 4d ago | |
| TREA rdete | QMIX | Mean Episodic Reward-390 | 21 | 4d ago | |
| REF rdete | MADDPG | Mean Episodic Reward-44 | 21 | 4d ago | |
| CN rdete | DRE-MARL | Mean Episodic Reward-154 | 21 | 4d ago | |
| SMAC v2 (test) | Win Rate (Protoss 5 Units)84 | 20 | 4d ago | ||
| SMAC Avg. v1 | MAST | Normalized Win Rate1.006 | 18 | 4d ago | |
| SMAC 6h* v1 | MAST | Normalized Win Rate104.9 | 18 | 4d ago | |
| SMAC 3s5z v1 | MAST | Normalized Win Rate99.4 | 18 | 4d ago | |
| SMAC 2s3z v1 | MAST | Normalized Win Rate100.2 | 18 | 4d ago | |
| SMAC 3m v1 | MAST | Normalized Win Rate100.9 | 18 | 4d ago | |
| SMAC maps | dmix-DA | 5m_vs_6m Score59 | 18 | 4d ago | |
| StarCraft Multi-Agent Challenge (SMAC) | MAPPO | 1c3s5z Win Rate100 | 13 | 4d ago | |
| SMAC 2m1z | SIPO-RBF | State Entropy0.038 | 12 | 3d ago | |
| Multi-Agent MuJoCo HalfCheetah fore thigh | MAT | Average Score8,347 | 12 | 4d ago | |
| Multi-Agent MuJoCo HalfCheetah fore shin | MAT | Average Evaluation Score4,373 | 12 | 4d ago | |
| Multi-Agent MuJoCo HalfCheetah fore foot | MAT | Average Evaluation Score6,054 | 12 | 4d ago | |
| Multi-Agent MuJoCo HalfCheetah back thigh | MAT | Avg Score7,460 | 12 | 4d ago | |
| Multi-Agent MuJoCo HalfCheetah back shin | MAT | Average Return7,176 | 12 | 4d ago | |
| Multi-Agent MuJoCo HalfCheetah back foot | MAT | Average Score5,646 | 12 | 4d ago | |
| REF-q rac-dist (test) | QMIX | Mean Episodic Reward (q=2)125 | 12 | 4d ago | |
| CN-q rac-dist (test) | DRE-MARL | Mean Episodic Reward (q=3)144 | 12 | 4d ago |
