Offline Reinforcement Learning on D4RL hopper-random v2
38.1Normalized ScoreMOREL
Evaluation results
| Method | Links | |
|---|---|---|
| MOREL2022.10 | 38.1 | |
| MOReL2022.10 | 38.1 | |
| MOReLModel category=Model-based2026.05 | 38.1 | |
| PhyBModel category=Model-based2026.05 | 33.9 | |
| RAMBO2022.10 | 32.7 | |
| PMDBN=10, k=22022.10 | 32.7 | |
| PMDBModel category=Model-based2026.05 | 32.7 | |
| ADMModel category=Model-based2026.05 | 32.7 | |
| EPQModel category=Model-free2026.05 | 32.1 | |
| Uncertainty-Aware Rank-One MIMO Q Network2026.02 | 31.3 | |
| PBRL2026.02 | 26.8 | |
| RAMBOModel category=Model-based2026.05 | 25.4 | |
| EDAC2022.10 | 25.3 | |
| EDAC2022.10 | 25.3 | |
| PMDB2022.10 | 22 | |
| DMGModel category=Model-free2026.05 | 20.4 | |
| EDAC-102026.02 | 16.9 | |
| MOPO2026.02 | 16.7 | |
| IQL2026.02 | 11.1 | |
| TD3+BCModel category=Model-free2026.05 | 11 | |
| BCQ2026.02 | 10.5 | |
| FQLModel category=Model-free2026.05 | 9.6 | |
| TD3-BC2026.02 | 8.5 | |
| BRAC2022.10 | 8.1 | |
| BRAC2022.10 | 8.1 | |
| CQL2026.02 | 7.9 | |
| CQL2022.10 | 5.3 | |
| CQL2022.10 | 5.3 | |
| CQLModel category=Model-free2026.05 | 5.3 | |
| BEAR2026.02 | 3.9 | |
| BC2022.10 | 3.7 | |
| BC2022.10 | 3.7 | |
| BEAR2022.10 | 3.6 | |
| BEAR2022.10 | 3.6 | |
| UWAV2026.02 | 2.7 |