Offline-to-online Reinforcement Learning on D4RL hopper-mr
113.5Final Online ScoreMoMa QL
Evaluation results
| Method | Links | |
|---|---|---|
| MoMa QL2026.05 | 113.5 | |
| AWAC2026.05 | 96 | |
| ACA2026.05 | 85.5 | |
| Consistency-AC2026.05 | 74.6 | |
| SAC2026.05 | 74 | |
| Diffusion-QL2026.05 | 68.4 |
| Method | Links | |
|---|---|---|
| MoMa QL2026.05 | 113.5 | |
| AWAC2026.05 | 96 | |
| ACA2026.05 | 85.5 | |
| Consistency-AC2026.05 | 74.6 | |
| SAC2026.05 | 74 | |
| Diffusion-QL2026.05 | 68.4 |