Locomotion on HalfCheetah Mass Scale 1.0x
9,602Cumulative RewardSO-CMA
Evaluation Results
| Method | Links | |
|---|---|---|
| SO-CMAEvaluation Protocol=Test-time Optimization2026.06 | 9,602 | |
| RMA (Phase 1)Evaluation Protocol=Source-only + Zero-shot, Adaptation Phase=Phase 12026.06 | 9,589 | |
| RMA (Phase 2)Evaluation Protocol=Source-only + Zero-shot, Adaptation Phase=Phase 22026.06 | 9,281 | |
| LDGEvaluation Protocol=Source-only + Zero-shot2026.06 | 8,022 | |
| VAEEvaluation Protocol=Source-only + Zero-shot2026.06 | 6,466 | |
| SAC+DREvaluation Protocol=Source-only + Zero-shot2026.06 | 5,753 |