Locomotion on D4RL hopper-medium-expert v2
111.9ReturnFTB
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FTB2026.06 | 111.9 | — | |
| LiRE2026.06 | 106.3 | — | |
| VOTP2026.06 | 105.7 | — | |
| IQL+GT2026.06 | 104.5 | — | |
| Oracle2026.06 | 101.9 | — | |
| P-IQL2026.06 | 89.1 | — | |
| DPPO2026.06 | 70.1 | — | |
| SURF2026.06 | 65.5 | — | |
| IPL2026.06 | 62.6 | — | |
| CPL2026.06 | 54.2 | — | |
| APPO2026.06 | 40.7 | — | |
| DACERTime steps=1M, Number of random seeds=52026.05 | — | 113.88 | |
| Diff-QLTime steps=1M, Number of random seeds=52026.05 | — | 110.94 | |
| DiffuserTime steps=1M, Number of random seeds=52026.05 | — | 106.73 | |
| DUALTime steps=1M, Number of random seeds=52026.05 | — | 115.33 | |
| EDISTime steps=1M, Number of random seeds=52026.05 | — | 109.93 | |
| IQLTime steps=1M, Number of random seeds=52026.05 | — | 107.48 |