Locomotion on D4RL walker2d-medium-expert
5,421.3Normalized ScoreUni-O4
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Uni-O42026.05 | 5,421.3 | — | |
| Onestep RL2026.05 | 5,189.1 | — | |
| Cal-QL2026.05 | 5,102.7 | — | |
| TD3+BC2026.05 | 5,056 | — | |
| COOPO2026.05 | 5,042.8 | — | |
| IQL2026.05 | 5,033 | — | |
| CQL2026.05 | 4,996.3 | — | |
| BC2026.05 | 4,936.6 | — | |
| AWAC2026.05 | 4,643.2 | — | |
| Off2ON2026.05 | 3,934.8 | — | |
| PEX2026.05 | 3,205.1 | — | |
| ODT2026.05 | 3,040 | — | |
| O2PPOOnline update way=IQL2024.12 | 121.4 | 9.35 | |
| O2SACOnline update way=SAC2024.12 | 120.95 | 11.51 | |
| Off2OnOnline update way=SAC2024.12 | 118.01 | 8.51 | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 113 | — | |
| OFQLCategory=One-step Flow Policies2025.08 | 113 | — | |
| A2PO2024.03 | 112.1 | — | |
| DMEMM2026.02 | 111.6 | — | |
| PRDC2024.03 | 111.2 | — | |
| IDQLCategory=Multi-step Diffusion Policies2025.08 | 110.6 | — | |
| IQL+ReD2024.03 | 110.5 | — | |
| EDPCategory=Multi-step Diffusion Policies2025.08 | 110.4 | — | |
| BiTrajDiffRL Algorithm=CQL2025.06 | 110.4 | — | |
| BaseRL Algorithm=CQL2025.06 | 110.2 | — | |
| TD3+BCMethod Category=Best RL Baseline, Seeds=52022.10 | 110.1 | — | |
| TD3-BCCategory=Non-Diffusion Policies2025.08 | 110.1 | — | |
| DQLCategory=Multi-step Diffusion Policies2025.08 | 110.1 | — | |
| RTDiffRL Algorithm=CQL2025.06 | 110.1 | — | |
| SyntherRL Algorithm=CQL2025.06 | 110.1 | — | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 109.6 | — | |
| IQL2023.12 | 109.6 | — | |
| IQL2026.02 | 109.6 | — | |
| IQLCategory=Non-Diffusion Policies2025.08 | 109.6 | — | |
| IQL2026.02 | 109.6 | — | |
| IQL2026.03 | 109.6 | — | |
| SAGE2026.03 | 109.4 | — | |
| DiffStitchRL Algorithm=CQL2025.06 | 109.4 | — | |
| LDCQ2026.03 | 109.3 | — | |
| LoMAP2026.03 | 109.2 | — | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 109.1 | — | |
| ISCTSeeds=5, Episodes=102026.02 | 109.1 | — | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 109 | — | |
| %BC2024.03 | 109 | — | |
| DD2023.12 | 108.8 | — | |
| CQL2026.02 | 108.8 | — | |
| CQL2026.02 | 108.8 | — | |
| CQL2026.03 | 108.8 | — | |
| DVreproduced=true2026.03 | 108.6 | — | |
| Diffuser2023.12 | 108.4 | — | |
| DDCategory=Diffusion Planners2025.08 | 108.4 | — | |
| DTAMP2023.12 | 108.2 | — | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 108.1 | — | |
| DT2023.12 | 108.1 | — | |
| DT2024.03 | 108.1 | — | |
| DT2026.02 | 108.1 | — | |
| DT2026.02 | 108.1 | — | |
| DT2026.03 | 108.1 | — | |
| HDMI2026.02 | 107.9 | — | |
| IMLE+Exp RW2026.03 | 107.9 | — | |
| RGG2026.03 | 107.8 | — | |
| CQL2023.12 | 107.5 | — | |
| BCCategory=Non-Diffusion Policies2025.08 | 107.5 | — | |
| BC2026.02 | 107.5 | — | |
| BC2026.03 | 107.5 | — | |
| DiffuserCategory=Diffusion Planners2025.08 | 107.4 | — | |
| HD-DA2026.02 | 107.1 | — | |
| Diffuser2026.02 | 106.9 | — | |
| Diffuserreproduced=true2026.03 | 106.9 | — | |
| Diffuser2026.03 | 106.9 | — | |
| BiTrajDiffRL Algorithm=DT2025.06 | 106.3 | — | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 106 | — | |
| SyntherRL Algorithm=DT2025.06 | 105.7 | — | |
| BaseRL Algorithm=DT2025.06 | 104.6 | — | |
| DiffStitchRL Algorithm=DT2025.06 | 104 | — | |
| TT2023.12 | 101.9 | — | |
| TT2026.02 | 101.9 | — | |
| TT2026.03 | 101.9 | — | |
| RTDiffRL Algorithm=DT2025.06 | 101.2 | — | |
| TD3+BC2026.02 | 101.1 | — | |
| FQLCategory=One-step Flow Policies2025.08 | 100.5 | — | |
| BestPhase=Offline2026.05 | 100 | — | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 100 | — | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 96.7 | — | |
| MOReL2026.02 | 95.6 | — | |
| MOReL2026.03 | 95.6 | — | |
| MBOP2026.03 | 70.2 | — | |
| MOPO2026.03 | 44.6 | — | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 28 | — | |
| OPEPhase=Offline2026.05 | 22.7 | — |