Reinforcement Learning on D4RL Hopper Medium-Expert
77.2Mean Normalized ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=160 K2026.05 | 77.2 | |
| BestPhase=Offline, Online Interaction Budget=160 K2026.05 | 74 | |
| OEPhase=Offline, Online Interaction Budget=160 K2026.05 | 73.9 | |
| FTPhase=Online, Online Interaction Budget=160 K2026.05 | 33.6 | |
| OPEPhase=Offline, Online Interaction Budget=160 K2026.05 | 12.2 |