Locomotion on D4RL Ant Medium-Expert
99.1Mean ReturnBest
Evaluation Results
| Method | Links | |
|---|---|---|
| BestPhase=Offline2026.05 | 99.1 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 99.1 | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 97.2 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 58.2 | |
| OPEPhase=Offline2026.05 | 47.8 |