Locomotion on HalfCheetah Time-Varying Dynamics
9,407Cumulative RewardRMA (Phase 1)
Evaluation Results
| Method | Links | |
|---|---|---|
| RMA (Phase 1)Evaluation Protocol=Source-only + Zero-shot, Adaptation Phase=Phase 12026.06 | 9,407 | |
| RMA (Phase 2)Evaluation Protocol=Source-only + Zero-shot, Adaptation Phase=Phase 22026.06 | 9,121 | |
| LDGEvaluation Protocol=Source-only + Zero-shot2026.06 | 7,849 | |
| VAEEvaluation Protocol=Source-only + Zero-shot2026.06 | 6,399 | |
| SAC+DREvaluation Protocol=Source-only + Zero-shot2026.06 | 5,769 | |
| SO-CMAEvaluation Protocol=Test-time Optimization2026.06 | 5,574 |