Offline-to-online Reinforcement Learning on D4RL halfcheetah-mr
96.3Final Online ScoreDiffusion-QL
Evaluation Results
| Method | Links | |
|---|---|---|
| Diffusion-QL2026.05 | 96.3 | |
| MoMa QL2026.05 | 80.9 | |
| Consistency-AC2026.05 | 80.7 | |
| SAC2026.05 | 68.9 | |
| ACA2026.05 | 59 | |
| AWAC2026.05 | 46.8 |
Loading the SOTA2 catalog…