Locomotion on D4RL Ant (Random)
85.1Mean ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 85.1 | |
| BestPhase=Offline2026.05 | 80.1 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 79.4 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 46.9 | |
| OPEPhase=Offline2026.05 | 8.7 |