Locomotion on D4RL MuJoCo walker2d-medium-replay v2
94.4Normalized ScoreSynthER
Evaluation Results
| Method | Links | |
|---|---|---|
| SynthERBase Policy=DiffQL2024.05 | 94.4 | |
| DiffQLData Augmentation=None2024.05 | 90.6 | |
| SynthERBase Policy=TD3BC2024.05 | 90.4 | |
| DyDiffBase Policy=DiffQL2024.05 | 90.2 | |
| DyDiffBase Policy=CQL2024.05 | 86.3 | |
| TD3BCData Augmentation=None2024.05 | 85.8 | |
| SynthERBase Policy=CQL2024.05 | 85.7 | |
| Geo-IQLSeeds=52026.02 | 82.1 | |
| CQLData Augmentation=None2024.05 | 80.5 | |
| IQLSeeds=52026.02 | 80.17 | |
| CQLSeeds=52026.02 | 78.28 | |
| DyDiffBase Policy=TD3BC2024.05 | 73.8 | |
| BCSeeds=52026.02 | 43.17 |