Locomotion on D4RL walker2d-medium-expert v2
112.62Average Online ReturnDUAL
Evaluation Results
| Method | Links | |
|---|---|---|
| DUALTime steps=1M, Number of random seeds=52026.05 | 112.62 | |
| Diff-QLTime steps=1M, Number of random seeds=52026.05 | 112.48 | |
| DACERTime steps=1M, Number of random seeds=52026.05 | 112.43 | |
| DiffuserTime steps=1M, Number of random seeds=52026.05 | 111.87 | |
| IQLTime steps=1M, Number of random seeds=52026.05 | 111.52 | |
| EDISTime steps=1M, Number of random seeds=52026.05 | 111.02 | |
| IQL+GT2026.06 | 109.9 | |
| LiRE2026.06 | 109.7 | |
| Oracle2026.06 | 109.6 | |
| VOTP2026.06 | 108.1 | |
| P-IQL2026.06 | 103.4 | |
| SURF2026.06 | 103.2 | |
| IPL2026.06 | 92.4 | |
| FTB2026.06 | 76.5 | |
| DPPO2026.06 | 70.2 | |
| CPL2026.06 | 39.9 | |
| APPO2026.06 | 31.2 |