Grasping on Robot Grasping Simulation
-12.43Episodic RewardIdeal
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| IdealOrder=NA2024.03 | -12.43 | 0.06 | 77 | |
| CDR-OλOrder=NLT2024.03 | -12.74 | 0.05 | 78 | |
| FinetuningOrder=NLT2024.03 | -12.96 | 0.07 | 59 | |
| CDR-λOrder=NLT2024.03 | -25.84 | 0.06 | 40 | |
| CDR-λOrder=TLN2024.03 | -27.63 | 0.08 | 40 | |
| RandomizedOrder=NA2024.03 | -28.42 | 0.04 | 20 | |
| FinetuningOrder=TLN2024.03 | -42.88 | 0.08 | 33 | |
| CDR-OλOrder=TLN2024.03 | -44.81 | 0.08 | 23 |