Offline-to-online Reinforcement Learning on D4RL hopper-me
98Final Online ScoreACA
Evaluation Results
| Method | Links | |
|---|---|---|
| ACA2026.05 | 98 | |
| MoMa QL2026.05 | 89.1 | |
| AWAC2026.05 | 73.1 | |
| Diffusion-QL2026.05 | 71.7 | |
| SAC2026.05 | 65.4 | |
| Consistency-AC2026.05 | 65.4 |
Loading the SOTA2 catalog…