Locomotion on D4RL Hopper-medium
100.42Normalized ScoreO2PPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| O2PPOOnline update way=IQL2024.12 | 100.42 | 48.61 | |
| O2TD3Online update way=TD32024.12 | 100.25 | 43.95 | |
| ACAOnline update way=SAC2024.12 | 99.76 | 41.08 | |
| TD3+BC2026.02 | 99.5 | — | |
| O2SACOnline update way=SAC2024.12 | 97.29 | 38 | |
| PEXOnline update way=IQL2024.12 | 95.7 | 33.59 | |
| MOReL2026.03 | 95.4 | — | |
| LoMAP2026.03 | 93.7 | — | |
| Cal-QLOnline update way=SAC2024.12 | 92.83 | 33.92 | |
| Off2OnOnline update way=SAC2024.12 | 90.34 | 29.83 | |
| IMLE+Exp RW2026.03 | 85 | — | |
| SAGE2026.03 | 83.9 | — | |
| RGG2026.03 | 82.5 | — | |
| AWACOnline update way=IQL2024.12 | 82.42 | 16.53 | |
| DVreproduced=true2026.03 | 80.9 | — | |
| Diffuserreproduced=true2026.03 | 74.3 | — | |
| Diffuser2026.03 | 74.3 | — | |
| DT2026.02 | 67.6 | — | |
| DT2026.03 | 67.6 | — | |
| IQL2026.02 | 66.3 | — | |
| IQL2026.03 | 66.3 | — | |
| LDCQ2026.03 | 66.2 | — | |
| TT2026.03 | 61.1 | — | |
| IQLOnline update way=IQL2024.12 | 60.48 | -1.62 | |
| ISCTSeeds=5, Episodes=102026.02 | 58.8 | — | |
| CQL2026.02 | 58.5 | — | |
| CQL2026.03 | 58.5 | — | |
| BC2026.03 | 52.9 | — | |
| MBOP2026.03 | 48.8 | — | |
| MOPO2026.03 | 28 | — |