Locomotion on D4RL Ant Medium
82.5Mean ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 82.5 | |
| BestPhase=Offline2026.05 | 68.7 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 68.7 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 48.6 | |
| OPEPhase=Offline2026.05 | 33 |