Offline Reinforcement Learning on MuJoCo D4RL (Aggregate)
82.9Mean Normalized ScoreDMM
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DMMModel Category=SSM-based2026.02 | 82.9 | 2.33 | |
| DCModel Category=SSM-based2026.02 | 81.4 | 2.89 | |
| DMModel Category=SSM-based2026.02 | 78.9 | 4.89 | |
| CQLModel Category=Value-based2026.02 | 77.6 | 4.11 | |
| EDTModel Category=Transformer-based2026.02 | 76.9 | 5.56 | |
| DTModel Category=Transformer-based2026.02 | 75.4 | 5.89 | |
| TD3+BCModel Category=Value-based2026.02 | 75.3 | 3.78 | |
| DS4Model Category=SSM-based2026.02 | 68.6 | 6.44 | |
| QLDTModel Category=Transformer-based2026.02 | 66.3 | 8.44 |