Locomotion on Dog & Humanoid suite
0.897IQMWIMLE
Evaluation Results
| Method | Links | |
|---|---|---|
| WIMLETraining steps=1M2026.02 | 0.897 | |
| BROTraining steps=1M2026.02 | 0.864 | |
| SimBAV2Training steps=1M2026.02 | 0.808 | |
| WIMLETraining steps=500k2026.02 | 0.803 | |
| MR.QTraining steps=1M2026.02 | 0.796 | |
| SimBATraining steps=1M2026.02 | 0.773 | |
| SimBAV2Training steps=500k2026.02 | 0.601 | |
| MR.QTraining steps=500k2026.02 | 0.557 | |
| SimBATraining steps=500k2026.02 | 0.533 | |
| TD-MPC2Training steps=1M2026.02 | 0.527 | |
| WIMLETraining steps=200k2026.02 | 0.389 | |
| BROTraining steps=500k2026.02 | 0.355 | |
| TD-MPC2Training steps=500k2026.02 | 0.302 | |
| BROTraining steps=200k2026.02 | 0.29 | |
| SimBAV2Training steps=200k2026.02 | 0.2 | |
| SimBATraining steps=200k2026.02 | 0.173 | |
| WIMLETraining steps=100k2026.02 | 0.14 | |
| MR.QTraining steps=200k2026.02 | 0.127 | |
| BROTraining steps=100k2026.02 | 0.086 | |
| SimBAV2Training steps=100k2026.02 | 0.082 | |
| SACTraining steps=1M2026.02 | 0.069 | |
| SimBATraining steps=100k2026.02 | 0.067 | |
| TD-MPC2Training steps=200k2026.02 | 0.058 | |
| SACTraining steps=500k2026.02 | 0.043 | |
| MR.QTraining steps=100k2026.02 | 0.042 | |
| TD-MPC2Training steps=100k2026.02 | 0.014 | |
| DreamerV3Training steps=1M2026.02 | 0.01 | |
| SACTraining steps=200k2026.02 | 0.008 | |
| SACTraining steps=100k2026.02 | 0.007 | |
| DreamerV3Training steps=500k2026.02 | 0.007 | |
| DreamerV3Training steps=100k2026.02 | 0.006 | |
| DreamerV3Training steps=200k2026.02 | 0.006 |