Offline Reinforcement Learning on D4RL Medium Hopper
109.4Normalized ScoreRRPI
Evaluation Results
| Method | Links | |
|---|---|---|
| RRPINumber of random seeds=42026.03 | 109.4 | |
| PSPOAveraged across=4 random seeds2026.05 | 108.5 | |
| AMGNumber of random seeds=42026.03 | 107.4 | |
| ADM2026.05 | 107.4 | |
| PMDBNumber of random seeds=42026.03 | 106.8 | |
| PMDBMethod Type=Model-based2023.10 | 106.8 | |
| PMDB2026.05 | 106.8 | |
| CABI+TD3-BCMethod Type=Model-based2023.10 | 105 | |
| Count-MORLMethod Type=Model-based2023.10 | 103.6 | |
| CROPMethod Type=Model-based2023.10 | 102.1 | |
| EDACMethod Type=Model-free2023.10 | 101.6 | |
| EPQNumber of random seeds=42026.03 | 101.3 | |
| EPQ2026.05 | 101.3 | |
| DMGNumber of random seeds=42026.03 | 100.6 | |
| DMG2026.05 | 100.6 | |
| DMambasource=Lv et al., 20242023.06 | 98.5 | |
| MPDiffuser+Rankranking=true2025.12 | 98.4 | |
| MPDiffuserranking=false2025.12 | 97.9 | |
| Planner2025.12 | 97.6 | |
| COMBO2025.12 | 97.2 | |
| COMBOMethod Type=Model-based2023.10 | 97.2 | |
| MOREL2023.06 | 95.4 | |
| MOReL2026.03 | 95.4 | |
| RAMBOMethod Type=Model-based2023.10 | 92.8 | |
| DQLNFE=52026.03 | 90.5 | |
| KDPNFE=12026.03 | 90.3 | |
| RAMBONumber of random seeds=42026.03 | 87 | |
| RAMBO2026.05 | 87 | |
| MambaDM2023.06 | 85.7 | |
| ATACMethod Type=Model-free2023.10 | 85.6 | |
| MOReLNumber of random seeds=42026.03 | 84 | |
| MOReL2026.05 | 84 | |
| DMambasource=Ota, 20242023.06 | 83.5 | |
| DDImplementation=reproduced2023.06 | 81.2 | |
| CACNFE=22026.03 | 80.7 | |
| DDImplementation=Original2023.06 | 79.3 | |
| Decision Diffuser2025.12 | 79.3 | |
| RATE2023.06 | 77.4 | |
| Decision Stacks2023.06 | 76.6 | |
| DiffuserNFE=202026.03 | 74.3 | |
| CBCNFE=22026.03 | 71.7 | |
| DT2023.06 | 67.6 | |
| DT2025.12 | 67.6 | |
| DT2023.06 | 67.6 | |
| DT2026.03 | 67.6 | |
| IQL2023.06 | 66.3 | |
| IQL2026.03 | 66.3 | |
| IQLMethod Type=Model-free2023.10 | 66.3 | |
| TAP2023.06 | 63.4 | |
| DT2023.06 | 63.1 | |
| IDQL2025.12 | 63.1 | |
| Diffuser2023.06 | 62.2 | |
| CQLNumber of random seeds=42026.03 | 61.9 | |
| CQL2026.05 | 61.9 | |
| D-MPC2025.12 | 61.2 | |
| TT2023.06 | 61.1 | |
| TT2023.06 | 61.1 | |
| TT2026.03 | 61.1 | |
| CQL2023.06 | 58.5 | |
| Diffuser2023.06 | 58.5 | |
| Diffuser2025.12 | 58.5 | |
| CQL2026.03 | 58.5 | |
| CQL2023.06 | 58 | |
| Decision Stacks2023.06 | 57.7 | |
| TT2023.06 | 55.7 | |
| BC2023.06 | 52.9 | |
| BC2025.12 | 52.9 | |
| BC2026.03 | 52.9 | |
| MBOP2026.03 | 48.8 | |
| DD2023.06 | 38.1 | |
| BC2023.06 | 36.4 | |
| MOPO2026.03 | 28 |