Add robotics pipeline tag and improve documentation
Browse filesHi! I'm Niels from the Hugging Face community science team.
This PR adds the `pipeline_tag: robotics` to the metadata, which helps researchers find your work when filtering for robotics models on the Hub. I've also updated the model card to ensure the paper, code, and project page links are easily accessible, and included usage instructions from your GitHub repository.
Please review and merge if this looks good to you!
README.md
CHANGED
|
@@ -1,18 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
| 3 |
tags:
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
|
| 8 |
---
|
| 9 |
|
| 10 |
# SkiP — Pretrained Checkpoints (RLBench-10)
|
| 11 |
|
| 12 |
-
Pretrained checkpoints for **SkiP (Skip Policy)** on 10 RLBench tasks.
|
| 13 |
|
| 14 |
SkiP dynamically leaps over redundant free-space steps and concentrates control on contact-rich key segments via action relabeling — no learned skip planner or hierarchical structure required.
|
| 15 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 16 |
## Checkpoints
|
| 17 |
|
| 18 |
| File | Task |
|
|
@@ -58,10 +65,4 @@ python scripts/eval.py task=open_drawer snapshot=checkpoints/open_drawer.pt
|
|
| 58 |
primaryClass={cs.RO},
|
| 59 |
url={https://arxiv.org/abs/2605.15536},
|
| 60 |
}
|
| 61 |
-
```
|
| 62 |
-
|
| 63 |
-
## Links
|
| 64 |
-
|
| 65 |
-
- [Paper](https://arxiv.org/abs/2605.15536)
|
| 66 |
-
- [Code](https://github.com/CCCalcifer/Skip-Policy)
|
| 67 |
-
- [Project Page](https://pgq18.github.io/SkiP-page/)
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
pipeline_tag: robotics
|
| 4 |
tags:
|
| 5 |
+
- robotics
|
| 6 |
+
- manipulation
|
| 7 |
+
- rlbench
|
| 8 |
+
- imitation-learning
|
| 9 |
---
|
| 10 |
|
| 11 |
# SkiP — Pretrained Checkpoints (RLBench-10)
|
| 12 |
|
| 13 |
+
Pretrained checkpoints for **SkiP (Skip Policy)** on 10 RLBench tasks, as presented in the paper [SkiP: When to Skip and When to Refine for Efficient Robot Manipulation](https://arxiv.org/abs/2605.15536).
|
| 14 |
|
| 15 |
SkiP dynamically leaps over redundant free-space steps and concentrates control on contact-rich key segments via action relabeling — no learned skip planner or hierarchical structure required.
|
| 16 |
|
| 17 |
+
## Links
|
| 18 |
+
|
| 19 |
+
- **Paper:** [https://arxiv.org/abs/2605.15536](https://arxiv.org/abs/2605.15536)
|
| 20 |
+
- **Code:** [https://github.com/CCCalcifer/Skip-Policy](https://github.com/CCCalcifer/Skip-Policy)
|
| 21 |
+
- **Project Page:** [https://pgq18.github.io/SkiP-page/](https://pgq18.github.io/SkiP-page/)
|
| 22 |
+
|
| 23 |
## Checkpoints
|
| 24 |
|
| 25 |
| File | Task |
|
|
|
|
| 65 |
primaryClass={cs.RO},
|
| 66 |
url={https://arxiv.org/abs/2605.15536},
|
| 67 |
}
|
| 68 |
+
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|