Locomotion on D4RL MuJoCo halfcheetah-medium-replay v2
47.7Normalized ScoreDyDiff
Evaluation Results
| Method | Links | |
|---|---|---|
| DyDiffBase Policy=DiffQL2024.05 | 47.7 | |
| DyDiffBase Policy=TD3BC2024.05 | 47.5 | |
| TD3BCData Augmentation=None2024.05 | 46 | |
| SynthERBase Policy=DiffQL2024.05 | 46 | |
| CQLSeeds=52026.02 | 45.41 | |
| SynthERBase Policy=TD3BC2024.05 | 45.2 | |
| DiffQLData Augmentation=None2024.05 | 45.1 | |
| IQLSeeds=52026.02 | 43.68 | |
| SynthERBase Policy=CQL2024.05 | 43.2 | |
| CQLData Augmentation=None2024.05 | 42.9 | |
| Geo-IQLSeeds=52026.02 | 42.52 | |
| DyDiffBase Policy=CQL2024.05 | 41.6 | |
| BCSeeds=52026.02 | 27.69 |