Locomotion on D4RL Ant Medium-Replay
78.9Mean ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 78.9 | |
| BestPhase=Offline2026.05 | 73.3 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 73.3 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 54.7 | |
| OPEPhase=Offline2026.05 | 26.6 |