hopper locomotion on D4RL hopper medium-expert
115.9Normalized ScoreDMEMM
Evaluation Results
| Method | Links | |
|---|---|---|
| DMEMM2026.02 | 115.9 | |
| HD-DA2026.02 | 115.3 | |
| HDMI2026.02 | 113.5 | |
| A2PO2024.03 | 113.4 | |
| BC2021.02 | 111.9 | |
| DD2023.12 | 111.8 | |
| COMBO2021.02 | 111.1 | |
| CQL2021.02 | 111 | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 110.9 | |
| %BC2024.03 | 110.9 | |
| TT2023.12 | 110 | |
| TT2026.02 | 110 | |
| TT2026.03 | 110 | |
| DTAMP2023.12 | 109.4 | |
| PRDC2024.03 | 109.2 | |
| MOREL2021.02 | 108.7 | |
| MOReL2026.02 | 108.7 | |
| MOReL2026.03 | 108.7 | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 107.6 | |
| DT2023.12 | 107.6 | |
| DT2026.02 | 107.6 | |
| DT2026.03 | 107.6 | |
| Diffuser2023.12 | 107.2 | |
| CQLMethod Category=Best RL Baseline, Seeds=52022.10 | 105.4 | |
| CQL2026.02 | 105.4 | |
| CQL2026.03 | 105.4 | |
| IMLE+Exp RW2026.03 | 104.2 | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 103.3 | |
| Diffuser2026.02 | 103.3 | |
| Diffuser2026.03 | 103.3 | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 101.7 | |
| IQL+ReD2024.03 | 101 | |
| BEAR2021.02 | 96.3 | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 91.5 | |
| IQL2023.12 | 91.5 | |
| IQL2026.02 | 91.5 | |
| IQL2026.03 | 91.5 | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 90 | |
| DT2024.03 | 82.7 | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 75.4 | |
| BestPhase=Offline2026.05 | 70.7 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 70.5 | |
| MBOP2026.03 | 55.1 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 52.7 | |
| CQL2023.12 | 52.5 | |
| BC2026.02 | 52.5 | |
| BC2026.03 | 52.5 | |
| MOPO2021.02 | 23.7 | |
| MOPO2026.03 | 23.7 | |
| OPEPhase=Offline2026.05 | 11.6 | |
| BRAC-p2021.02 | 1.9 | |
| SAC-off2021.02 | 1.6 | |
| BRAC-v2021.02 | 0.8 |