Offline Reinforcement Learning on D4RL Gym halfcheetah medium, medium-replay, medium-expert
80.9Normalized ScoreMoMa QL
Evaluation results
| Method | Links | |
|---|---|---|
| MoMa QL2026.05 | 80.9 | |
| Consistency-AC2026.05 | 70.7 | |
| Diffusion-QL2026.05 | 65.2 | |
| IDQL-A2026.05 | 64.3 | |
| X-QL2026.05 | 62.6 | |
| CQL2026.05 | 60.4 | |
| IQL2026.05 | 59.4 | |
| ARQ2026.05 | 59.3 |