Locomotion on D4RL halfcheetah-medium-expert
105.9Normalized ScoreMBOP
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MBOP2026.03 | 105.9 | — | |
| O2SACOnline update way=SAC2024.12 | 100.41 | 6.24 | |
| Off2OnOnline update way=SAC2024.12 | 98.33 | 2.67 | |
| TD3+BC2026.02 | 97.9 | — | |
| A2PO2024.03 | 95.6 | — | |
| SAGE2026.03 | 95.4 | — | |
| TT2023.12 | 95 | — | |
| TT2026.02 | 95 | — | |
| TT2026.03 | 95 | — | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 94.7 | — | |
| DMEMM2026.02 | 94.6 | — | |
| PRDC2024.03 | 94.5 | — | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 93.4 | — | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 92.9 | — | |
| %BC2024.03 | 92.9 | — | |
| DVreproduced=true2026.03 | 92.7 | — | |
| IQL+ReD2024.03 | 92.6 | — | |
| HD-DA2026.02 | 92.5 | — | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 92.2 | — | |
| HDMI2026.02 | 92.1 | — | |
| IMLE+Exp RW2026.03 | 91.9 | — | |
| CQLMethod Category=Best RL Baseline, Seeds=52022.10 | 91.6 | — | |
| CQL2023.12 | 91.6 | — | |
| CQL2026.02 | 91.6 | — | |
| CQL2026.02 | 91.6 | — | |
| CQL2026.03 | 91.6 | — | |
| ISCTSeeds=5, Episodes=102026.02 | 91.4 | — | |
| LoMAP2026.03 | 91.1 | — | |
| RGG2026.03 | 90.8 | — | |
| DD2023.12 | 90.6 | — | |
| LDCQ2026.03 | 90.2 | — | |
| O2PPOOnline update way=IQL2024.12 | 89.61 | -3.29 | |
| Diffuser2026.02 | 88.9 | — | |
| Diffuserreproduced=true2026.03 | 88.9 | — | |
| Diffuser2026.03 | 88.9 | — | |
| DTAMP2023.12 | 88.2 | — | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 86.8 | — | |
| DT2023.12 | 86.8 | — | |
| DT2024.03 | 86.8 | — | |
| DT2026.02 | 86.8 | — | |
| DT2026.02 | 86.8 | — | |
| DT2026.03 | 86.8 | — | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 86.7 | — | |
| IQL2023.12 | 86.7 | — | |
| IQL2026.02 | 86.7 | — | |
| IQL2026.02 | 86.7 | — | |
| IQL2026.03 | 86.7 | — | |
| Diffuser2023.12 | 79.8 | — | |
| MOPO2026.03 | 63.3 | — | |
| BC2026.02 | 55.2 | — | |
| BC2026.03 | 55.2 | — | |
| MOReL2026.02 | 53.3 | — | |
| MOReL2026.03 | 53.3 | — |