Locomotion on D4RL Cheetah Medium
5,277.5Mean ReturnUni-O4
Evaluation Results
| Method | Links | |
|---|---|---|
| Uni-O42026.05 | 5,277.5 | |
| PEX2026.05 | 5,084.2 | |
| COOPO2026.05 | 4,947.1 | |
| Onestep RL2026.05 | 4,828.4 | |
| TD3+BC2026.05 | 4,822.7 | |
| Cal-QL2026.05 | 4,754.7 | |
| AWAC2026.05 | 4,531.1 | |
| IQL2026.05 | 4,520.6 | |
| CQL2026.05 | 4,371.2 | |
| ODT2026.05 | 4,235.4 | |
| BC2026.05 | 4,233.3 | |
| Off2ON2026.05 | 3,878.4 | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 91.8 | |
| BestPhase=Offline2026.05 | 89.7 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 89.6 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 72.8 | |
| OPEPhase=Offline2026.05 | 46.7 |