Reinforcement Learning on D4RL Walker Random
47.1Mean Normalized ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=160 K2026.05 | 47.1 | |
| BestPhase=Offline, Online Interaction Budget=160 K2026.05 | 45.1 | |
| OEPhase=Offline, Online Interaction Budget=160 K2026.05 | 41.2 | |
| FTPhase=Online, Online Interaction Budget=160 K2026.05 | 30.4 | |
| OPEPhase=Offline, Online Interaction Budget=160 K2026.05 | 13.6 |