Robotic Manipulation on Robomimic Transport (ph) 2D state-based
74Success Rate (Max Perf)Flow
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FlowNFE=9, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 74 | 59 | |
| DPNFE=100, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 73 | 62 | |
| IDPNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 72 | 58 | |
| MIPNFE=2, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 71 | 58 | |
| Naive DriftingNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 68 | 58 | |
| MP1NFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 52 | 39 | |
| CPNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 32 | 24 |