Offline Reinforcement Learning on D4RL halfcheetah-full-replay v2
98.1Normalized ScorePhyB
Evaluation Results
| Method | Links | |
|---|---|---|
| PhyBModel category=Model-based2026.05 | 98.1 | |
| PMDB2022.10 | 90 | |
| PMDBN=10, k=22022.10 | 90 | |
| PMDBModel category=Model-based2026.05 | 90 | |
| RAMBO2022.10 | 87 | |
| RAMBOModel category=Model-based2026.05 | 87 | |
| ADMModel category=Model-based2026.05 | 86.3 | |
| EPQModel category=Model-free2026.05 | 85.3 | |
| EDAC2022.10 | 84.6 | |
| EDAC2022.10 | 84.6 | |
| FQLModel category=Model-free2026.05 | 80.9 | |
| DMGModel category=Model-free2026.05 | 79.9 | |
| BRAC2022.10 | 78 | |
| CQL2022.10 | 76.9 | |
| CQL2022.10 | 76.9 | |
| CQLModel category=Model-free2026.05 | 76.9 | |
| BRAC2022.10 | 75.1 | |
| TD3+BCModel category=Model-free2026.05 | 71.9 | |
| MOREL2022.10 | 70.1 | |
| MOReL2022.10 | 70.1 | |
| MOReLModel category=Model-based2026.05 | 70.1 | |
| BC2022.10 | 62.9 | |
| BEAR2022.10 | 60.1 | |
| BEAR2022.10 | 60.1 | |
| BC2022.10 | 39.4 |