One-shot Imitation Learning on RLBench Oneshot 20 Unseen LH Tasks
30.2Avg Success RateManiLong-Shot
Evaluation Results
| Method | Links | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ManiLong-ShotEvaluation Protocol=One-shot, Number of Demonstrations=12025.12 | 30.2 | 1 | 28 | 42.7 | 37.3 | 48 | 18.7 | 14.7 | 24 | 30.7 | 26.7 | 65.3 | 76 | 28 | 18.7 | 42.7 | 29.3 | 12 | 9.3 | 17.3 | 8 | |
| IMOPEvaluation Protocol=One-shot, Number of Demonstrations=12025.12 | 7.4 | 2.6 | 4 | 1.3 | 2.7 | 5.3 | 1.3 | 2.7 | 4 | 4 | 5.3 | 40 | 38.7 | 4 | 1.3 | 9.3 | 1.3 | 1.3 | 1.3 | 2.7 | 1.3 | |
| ARPEvaluation Protocol=Fine-tuned, Number of Demonstrations=52025.12 | 4.7 | 3.3 | 1.3 | 2.7 | 5.3 | 0 | 2.7 | 0 | 4 | 4 | 5.3 | 18.7 | 37.3 | 8 | 0 | 0 | 2.7 | 0 | 1.3 | 0 | 0 | |
| 3DDAEvaluation Protocol=Fine-tuned, Number of Demonstrations=52025.12 | 4.5 | 3.3 | 1.6 | 1.3 | 1.6 | 1.2 | 4.3 | 1.3 | 5.3 | 5.3 | 0 | 29.3 | 30.7 | 0 | 0 | 0 | 1.3 | 4 | 1.3 | 0 | 0 | |
| RVT2Evaluation Protocol=Fine-tuned, Number of Demonstrations=52025.12 | 4.1 | 3.7 | 1.6 | 0 | 0 | 1.2 | 4 | 1.3 | 2.7 | 2.7 | 2.7 | 28 | 29.3 | 2.7 | 0 | 2.7 | 0 | 0 | 0 | 1.3 | 0 |