Offline Reinforcement Learning on D4RL hopper-full-replay v2
111Normalized ScorePhyB
Evaluation Results
| Method | Links | |
|---|---|---|
| PhyBModel category=Model-based2026.05 | 111 | |
| PMDB2022.10 | 109.1 | |
| PMDBN=10, k=22022.10 | 109.1 | |
| PMDBNumber of random seeds=42026.03 | 109.1 | |
| PMDBModel category=Model-based2026.05 | 109.1 | |
| RRPINumber of random seeds=42026.03 | 108.6 | |
| EPQNumber of random seeds=42026.03 | 108.5 | |
| AMGNumber of random seeds=42026.03 | 108.5 | |
| EPQModel category=Model-free2026.05 | 108.5 | |
| ADMModel category=Model-based2026.05 | 108.5 | |
| BRAC2022.10 | 107.4 | |
| DMGNumber of random seeds=42026.03 | 106.4 | |
| DMGModel category=Model-free2026.05 | 106.4 | |
| EDAC2022.10 | 105.4 | |
| EDAC2022.10 | 105.4 | |
| RAMBO2022.10 | 105.2 | |
| RAMBONumber of random seeds=42026.03 | 105.2 | |
| RAMBOModel category=Model-based2026.05 | 105.2 | |
| BRAC2022.10 | 101.9 | |
| CQL2022.10 | 101.9 | |
| CQLNumber of random seeds=42026.03 | 101.9 | |
| CQLModel category=Model-free2026.05 | 101.9 | |
| CQL2022.10 | 101 | |
| MOREL2022.10 | 94.4 | |
| MOReL2022.10 | 94.4 | |
| MOReLNumber of random seeds=42026.03 | 94.4 | |
| MOReLModel category=Model-based2026.05 | 94.4 | |
| FQLModel category=Model-free2026.05 | 89.6 | |
| TD3+BCModel category=Model-free2026.05 | 85.9 | |
| BEAR2022.10 | 54 | |
| BEAR2022.10 | 54 | |
| BC2022.10 | 19.9 | |
| BC2022.10 | 19.9 |