Offline Reinforcement Learning on D4RL halfcheetah-random v2
45.4Normalized ScoreADM
Evaluation results
| Method | Links | |
|---|---|---|
| ADMModel category=Model-based2026.05 | 45.4 | |
| RAMBO2022.10 | 39.5 | |
| RAMBOModel category=Model-based2026.05 | 39.5 | |
| MOREL2022.10 | 38.9 | |
| MOReL2022.10 | 38.9 | |
| MOReLModel category=Model-based2026.05 | 38.9 | |
| PMDB2022.10 | 37.8 | |
| PMDBN=10, k=22022.10 | 37.8 | |
| PMDBModel category=Model-based2026.05 | 37.8 | |
| MOPO2026.02 | 35.9 | |
| PhyBModel category=Model-based2026.05 | 34.7 | |
| EPQModel category=Model-free2026.05 | 33 | |
| Uncertainty-Aware Rank-One MIMO Q Network2026.02 | 31.5 | |
| CQL2022.10 | 31.3 | |
| CQL2022.10 | 31.3 | |
| CQLModel category=Model-free2026.05 | 31.3 | |
| DMGModel category=Model-free2026.05 | 28.8 | |
| EDAC2022.10 | 28.4 | |
| EDAC2022.10 | 28.4 | |
| BRAC2022.10 | 24.3 | |
| BRAC2022.10 | 24.3 | |
| CQL2026.02 | 17.5 | |
| IQL2026.02 | 14.4 | |
| FQLModel category=Model-free2026.05 | 14.2 | |
| EDAC-102026.02 | 13.4 | |
| BEAR2022.10 | 12.6 | |
| BEAR2022.10 | 12.6 | |
| TD3-BC2026.02 | 11 | |
| PBRL2026.02 | 11 | |
| TD3+BCModel category=Model-free2026.05 | 10.2 | |
| BCQ2026.02 | 2.3 | |
| BEAR2026.02 | 2.3 | |
| UWAV2026.02 | 2.3 | |
| BC2022.10 | 2.2 | |
| BC2022.10 | 2.2 |