Robotic Manipulation on Robomimic Can ph 2D state-based
100Success Rate (Max Performance)DP
Evaluation results
| Method | Links | ||
|---|---|---|---|
| DPNFE=100, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 100 | 98 | |
| FlowNFE=9, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 100 | 98 | |
| MIPNFE=2, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 100 | 98 | |
| MP1NFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 100 | 97 | |
| IDPNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 100 | 97 | |
| CPNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 99 | 96 | |
| Naive DriftingNFE=1, Observation Modality=2D state-based, Network Architecture=Transformer, CNN (average)2026.05 | 99 | 96 |