Hopper Locomotion on D4RL hopper medium-replay
105.12Normalized ScoreO2SAC
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| O2SACOnline update way=SAC2024.12 | 105.12 | 16.15 | |
| Off2OnOnline update way=SAC2024.12 | 103.61 | 4.93 | |
| OFQLCategory=One-step Flow Policies2025.08 | 101.9 | — | |
| A2PO2024.03 | 101.6 | — | |
| DQLCategory=Multi-step Diffusion Policies2025.08 | 101.3 | — | |
| IQL+ReD2024.03 | 101 | — | |
| DMEMM2026.02 | 100.6 | — | |
| PRDC2024.03 | 100.1 | — | |
| DD2023.12 | 100 | — | |
| DTAMP2023.12 | 100 | — | |
| HDMI2026.02 | 99.6 | — | |
| IDQLCategory=Multi-step Diffusion Policies2025.08 | 99.4 | — | |
| DDCategory=Diffusion Planners2025.08 | 99.2 | — | |
| PORMethod Category=Conditioned BC, Seeds=52022.10 | 98.9 | — | |
| One-step RLMethod Category=Weighted BC, Seeds=52022.10 | 97.5 | — | |
| O2PPOOnline update way=IQL2024.12 | 96.87 | 18.14 | |
| Diffuser2023.12 | 96.8 | — | |
| CQLMethod Category=Best RL Baseline, Seeds=52022.10 | 95 | — | |
| CQL2026.02 | 95 | — | |
| CQL2026.02 | 95 | — | |
| CQL2026.03 | 95 | — | |
| IQLMethod Category=Weighted BC, Seeds=52022.10 | 94.7 | — | |
| IQL2023.12 | 94.7 | — | |
| IQL2026.02 | 94.7 | — | |
| IQLCategory=Non-Diffusion Policies2025.08 | 94.7 | — | |
| IQL2026.02 | 94.7 | — | |
| HD-DA2026.02 | 94.7 | — | |
| IQL2026.03 | 94.7 | — | |
| MOREL2021.02 | 93.6 | — | |
| MOReL2026.02 | 93.6 | — | |
| Diffuser2026.02 | 93.6 | — | |
| MOReL2026.03 | 93.6 | — | |
| Diffuser2026.03 | 93.6 | — | |
| DiffuserCategory=Diffusion Planners2025.08 | 91.8 | — | |
| TT2023.12 | 91.5 | — | |
| TT2026.02 | 91.5 | — | |
| TT2026.03 | 91.5 | — | |
| COMBO2021.02 | 89.5 | — | |
| FQLCategory=One-step Flow Policies2025.08 | 85.4 | — | |
| IMLE+Exp RW2026.03 | 85 | — | |
| EDPCategory=Multi-step Diffusion Policies2025.08 | 83 | — | |
| DTMethod Category=Conditioned BC, Seeds=52022.10 | 82.7 | — | |
| DT2023.12 | 82.7 | — | |
| DT2024.03 | 82.7 | — | |
| DT2026.02 | 82.7 | — | |
| DT2026.02 | 82.7 | — | |
| DT2026.03 | 82.7 | — | |
| Adaptive Policy Selection and Fine-TuningPhase=Online, Online Interaction Budget=320 K2026.05 | 80.3 | — | |
| 10%BCMethod Category=Weighted BC, Seeds=52022.10 | 75.9 | — | |
| %BC2024.03 | 75.9 | — | |
| RvSMethod Category=Conditioned BC, Seeds=52022.10 | 73.5 | — | |
| ISCTSeeds=5, Episodes=102026.02 | 70.5 | — | |
| MOPO2021.02 | 67.5 | — | |
| MOPO2026.03 | 67.5 | — | |
| BestPhase=Offline2026.05 | 66.6 | — | |
| OEPhase=Online, Online Interaction Budget=320 K2026.05 | 66.1 | — | |
| FTPhase=Online, Online Interaction Budget=320 K2026.05 | 61.4 | — | |
| TD3-BCCategory=Non-Diffusion Policies2025.08 | 60.9 | — | |
| CQL2021.02 | 48.6 | — | |
| BEAR2021.02 | 33.7 | — | |
| TD3+BC2026.02 | 31.4 | — | |
| OPEPhase=Offline2026.05 | 24.8 | — | |
| CQL2023.12 | 18.1 | — | |
| BCCategory=Non-Diffusion Policies2025.08 | 18.1 | — | |
| BC2026.02 | 18.1 | — | |
| BC2026.03 | 18.1 | — | |
| MBOP2026.03 | 12.4 | — | |
| BC2021.02 | 11.8 | — | |
| SAC-off2021.02 | 3.5 | — | |
| BRAC-p2021.02 | 0.6 | — | |
| BRAC-v2021.02 | 0.6 | — |