Locomotion on D4RL walker2d-medium
88.1Normalized ScoreIDQL
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| IDQLCategory=Multi-step Diffusion Policies2025.08 | 88.1 | — | — | — | |
| OFQLCategory=One-step Flow Policies2025.08 | 87.4 | — | — | — | |
| DQLCategory=Multi-step Diffusion Policies2025.08 | 87 | — | — | — | |
| EDPCategory=Multi-step Diffusion Policies2025.08 | 86.5 | — | — | — | |
| DMEMM2026.02 | 86.5 | — | — | — | |
| PRDC2024.03 | 85.2 | — | — | — | |
| A2PO2024.03 | 84.9 | — | — | — | |
| SAGE2026.03 | 84.8 | — | — | — | |
| BiTrajDiffRL Algorithm=CQL2025.06 | 84.2 | — | — | — | |
| HD-DA2026.02 | 84 | — | — | — | |
| TD3-BCCategory=Non-Diffusion Policies2025.08 | 83.7 | — | — | — | |
| RTDiffRL Algorithm=CQL2025.06 | 83.5 | — | — | — | |
| SyntherRL Algorithm=CQL2025.06 | 83.4 | — | — | — | |
| DVreproduced=true2026.03 | 82.8 | — | — | — | |
| DTAMP2023.12 | 82.7 | — | — | — | |
| BaseRL Algorithm=CQL2025.06 | 82.6 | — | — | — | |
| DD2023.12 | 82.5 | — | — | — | |
| DiffStitchRL Algorithm=CQL2025.06 | 82.4 | — | — | — | |
| RGG2026.03 | 81.7 | — | — | — | |
| HDMI2026.02 | 79.9 | — | — | — | |
| LoMAP2026.03 | 79.9 | — | — | — | |
| ISCTSeeds=5, Episodes=102026.02 | 79.8 | — | — | — | |
| Diffuser2023.12 | 79.7 | — | — | — | |
| TD3+BC2026.02 | 79.7 | — | — | — | |
| DDCategory=Diffusion Planners2025.08 | 79.6 | — | — | — | |
| Diffuser2026.02 | 79.6 | — | — | — | |
| Diffuserreproduced=true2026.03 | 79.6 | — | — | — | |
| Diffuser2026.03 | 79.6 | — | — | — | |
| DiffuserCategory=Diffusion Planners2025.08 | 79.4 | — | — | — | |
| TT2023.12 | 79 | — | — | — | |
| TT2026.02 | 79 | — | — | — | |
| TT2026.03 | 79 | — | — | — | |
| IQL+ReD2024.03 | 78.6 | — | — | — | |
| IQL2023.12 | 78.3 | — | — | — | |
| IQL2026.02 | 78.3 | — | — | — | |
| IQLCategory=Non-Diffusion Policies2025.08 | 78.3 | — | — | — | |
| IQL2026.02 | 78.3 | — | — | — | |
| IQL2026.03 | 78.3 | — | — | — | |
| IMLE+Exp RW2026.03 | 78.3 | — | — | — | |
| MOReL2026.02 | 77.8 | — | — | — | |
| MOReL2026.03 | 77.8 | — | — | — | |
| BiTrajDiffRL Algorithm=DT2025.06 | 77.8 | — | — | — | |
| CQL2023.12 | 75.3 | — | — | — | |
| BCCategory=Non-Diffusion Policies2025.08 | 75.3 | — | — | — | |
| BC2026.02 | 75.3 | — | — | — | |
| BC2026.03 | 75.3 | — | — | — | |
| %BC2024.03 | 75 | — | — | — | |
| SyntherRL Algorithm=DT2025.06 | 74.8 | — | — | — | |
| DT2023.12 | 74 | — | — | — | |
| DT2024.03 | 74 | — | — | — | |
| DT2026.02 | 74 | — | — | — | |
| DT2026.02 | 74 | — | — | — | |
| DT2026.03 | 74 | — | — | — | |
| FQLCategory=One-step Flow Policies2025.08 | 72.7 | — | — | — | |
| CQL2026.02 | 72.5 | — | — | — | |
| CQL2026.02 | 72.5 | — | — | — | |
| CQL2026.03 | 72.5 | — | — | — | |
| DiffStitchRL Algorithm=DT2025.06 | 72.3 | — | — | — | |
| RTDiffRL Algorithm=DT2025.06 | 71.6 | — | — | — | |
| BaseRL Algorithm=DT2025.06 | 69.6 | — | — | — | |
| LDCQ2026.03 | 69.4 | — | — | — | |
| MBOP2026.03 | 41 | — | — | — | |
| MOPO2026.03 | 17.8 | — | — | — | |
| TD3+BCMethod Category=Best RL Baseline, Seeds=52022.10 | 0.837 | — | — | — | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 0.818 | — | — | — | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 0.811 | — | — | — | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 0.783 | — | — | — | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 0.75 | — | — | — | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 0.74 | — | — | — | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 0.717 | — | — | — | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | — | — | — | 89.6 | |
| AWAC2026.05 | — | — | — | 2,910.2 | |
| BC2026.05 | — | — | — | 2,748.3 | |
| BestPhase=Offline2026.05 | — | — | — | 90.9 | |
| Cal-QL2026.05 | — | — | — | 3,083.6 | |
| COOPO2026.05 | — | — | — | 3,570.4 | |
| CQL2026.05 | — | — | — | 2,651.3 | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | — | — | — | 31.4 | |
| IQL2026.05 | — | — | — | 2,718.4 | |
| O2PPOOnline update way=IQL2024.12 | — | 86.65 | 9 | — | |
| O2SACOnline update way=SAC2024.12 | — | 106.51 | 25.42 | — | |
| ODT2026.05 | — | — | — | 2,625.7 | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | — | — | — | 90 | |
| Off2OnOnline update way=SAC2024.12 | — | 98.2 | 17.55 | — | |
| Off2ON2026.05 | — | — | — | 2,413.6 | |
| Onestep RL2026.05 | — | — | — | 2,987.6 | |
| OPEPhase=Offline2026.05 | — | — | — | 24.4 | |
| PEX2026.05 | — | — | — | 2,922.4 | |
| TD3+BC2026.05 | — | — | — | 3,052 | |
| Uni-O42026.05 | — | — | — | 3,289.3 |