Offline Reinforcement Learning on D4RL Gym hopper medium, medium-replay, medium-expert
101Normalized ScoreDiffusion-QL
Evaluation results
| Method | Links | |
|---|---|---|
| Diffusion-QL2026.05 | 101 | |
| MoMa QL2026.05 | 99.9 | |
| X-QL2026.05 | 95.4 | |
| Consistency-AC2026.05 | 93.6 | |
| IDQL-A2026.05 | 88.7 | |
| CQL2026.05 | 86.3 | |
| IQL2026.05 | 84.2 | |
| ARQ2026.05 | 84 |