Offline Reinforcement Learning on D4RL walker2d full-replay v2
107.4Normalized ScoreEPQ
Evaluation results
| Method | Links | |
|---|---|---|
| EPQNumber of random seeds=42026.03 | 107.4 | |
| EPQModel category=Model-free2026.05 | 107.4 | |
| RRPINumber of random seeds=42026.03 | 107.3 | |
| AMGNumber of random seeds=42026.03 | 99.9 | |
| ADMModel category=Model-based2026.05 | 99.9 | |
| EDAC2022.10 | 99.8 | |
| EDAC2022.10 | 99.8 | |
| PhyBModel category=Model-based2026.05 | 99.7 | |
| DMGNumber of random seeds=42026.03 | 97.5 | |
| DMGModel category=Model-free2026.05 | 97.5 | |
| BRAC2022.10 | 96.9 | |
| BRAC2022.10 | 96.9 | |
| PMDB2022.10 | 95.4 | |
| PMDBN=10, k=22022.10 | 95.4 | |
| PMDBNumber of random seeds=42026.03 | 95.4 | |
| PMDBModel category=Model-based2026.05 | 95.4 | |
| CQL2022.10 | 94.2 | |
| CQL2022.10 | 94.2 | |
| CQLNumber of random seeds=42026.03 | 94.2 | |
| CQLModel category=Model-free2026.05 | 94.2 | |
| TD3+BCModel category=Model-free2026.05 | 92 | |
| RAMBO2022.10 | 88.3 | |
| RAMBONumber of random seeds=42026.03 | 88.3 | |
| RAMBOModel category=Model-based2026.05 | 88.3 | |
| MOREL2022.10 | 84.8 | |
| MOReL2022.10 | 84.8 | |
| MOReLNumber of random seeds=42026.03 | 84.8 | |
| MOReLModel category=Model-based2026.05 | 84.8 | |
| BEAR2022.10 | 79.6 | |
| BEAR2022.10 | 79.6 | |
| BC2022.10 | 68.8 | |
| BC2022.10 | 68.8 | |
| FQLModel category=Model-free2026.05 | 42.2 |