Unknotting on DLO-Lab
57.21Maximum Episodic ReturnCMA-ES
Evaluation Results
| Method | Links | |
|---|---|---|
| CMA-ESAlgorithm Type=Trajectory optimization2026.06 | 57.21 | |
| SAPOAlgorithm Type=First-order model-based reinforcement learning (FO-MBRL)2026.06 | 46.3 | |
| SHACAlgorithm Type=First-order model-based reinforcement learning (FO-MBRL)2026.06 | 45.88 | |
| GDAlgorithm Type=Trajectory optimization2026.06 | 3.44 | |
| PPOAlgorithm Type=Model-free reinforcement learning (MFRL)2026.06 | 3.29 | |
| SACAlgorithm Type=Model-free reinforcement learning (MFRL)2026.06 | 2.95 |