Reinforcement Learning on D4RL Ant Medium-Replay
81.8Mean Normalized ReturnAdaptive Policy Selection and Fine-Tuning
Evaluation Results
| Method | Links | |
|---|---|---|
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=160 K2026.05 | 81.8 | |
| BestPhase=Offline, Online Interaction Budget=160 K2026.05 | 77.4 | |
| OEPhase=Offline, Online Interaction Budget=160 K2026.05 | 77.4 | |
| FTPhase=Online, Online Interaction Budget=160 K2026.05 | 37.6 | |
| OPEPhase=Offline, Online Interaction Budget=160 K2026.05 | 29.1 |