Reinforcement Learning on D4RL Cheetah Medium
92Mean Normalized ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=160 K2026.05 | 92 | |
| BestPhase=Offline, Online Interaction Budget=160 K2026.05 | 90 | |
| OEPhase=Offline, Online Interaction Budget=160 K2026.05 | 89.8 | |
| FTPhase=Online, Online Interaction Budget=160 K2026.05 | 56.9 | |
| OPEPhase=Offline, Online Interaction Budget=160 K2026.05 | 46.9 |