Locomotion on Walker2d (in-distribution)
4,883.7Mean Cumulative RewardLDG
Evaluation Results
| Method | Links | |
|---|---|---|
| LDGAccess Regime=Source-only + Zero-shot2026.06 | 4,883.7 | |
| RMA (Phase 2)Access Regime=Source-only + Zero-shot2026.06 | 3,193.6 | |
| SAC+DRAccess Regime=Source-only + Zero-shot2026.06 | 3,170.2 | |
| RMA (Phase 1)Access Regime=Source-only + Zero-shot2026.06 | 3,132.4 | |
| VAEAccess Regime=Source-only + Zero-shot2026.06 | 2,462.4 | |
| SO-CMAAccess Regime=Test-time opt.2026.06 | 2,281.9 |