Locomotion on Ant (in-distribution)
5,183.9Mean Cumulative RewardLDG
Evaluation Results
| Method | Links | |
|---|---|---|
| LDGAccess Regime=Source-only + Zero-shot2026.06 | 5,183.9 | |
| SO-CMAAccess Regime=Test-time opt.2026.06 | 5,042.9 | |
| SAC+DRAccess Regime=Source-only + Zero-shot2026.06 | 4,729.8 | |
| RMA (Phase 2)Access Regime=Source-only + Zero-shot2026.06 | 4,107.8 | |
| RMA (Phase 1)Access Regime=Source-only + Zero-shot2026.06 | 3,817.7 | |
| VAEAccess Regime=Source-only + Zero-shot2026.06 | 2,887.9 |