Views
No views yet
| File | Task |
|---|---|
| checkpoints/open_box.pt | open_box |
| checkpoints/open_drawer.pt | open_drawer |
| checkpoints/pick_up_cup.pt | pick_up_cup |
| checkpoints/press_switch.pt | press_switch |
| checkpoints/push_button.pt | push_button |
| checkpoints/reach_target.pt | reach_target |
| checkpoints/stack_wine.pt | stack_wine |
| checkpoints/sweep_to_dustpan.pt | sweep_to_dustpan |
| checkpoints/take_lid_off_saucepan.pt | take_lid_off_saucepan |
| checkpoints/turn_tap.pt | turn_tap |
1# Install
2git clone https://github.com/CCCalcifer/Skip-Policy.git && cd Skip-Policy
3bash scripts/init.sh
4
5# One-click eval (auto-downloads checkpoint + data)
6bash scripts/eval.sh task=push_button
7
8# Or manually download and eval
9pip install huggingface_hub
10python -c "from huggingface_hub import hf_hub_download; hf_hub_download('AYouZhuA/SkiP-RLBench', 'checkpoints/open_drawer.pt', local_dir='.')"
11python scripts/eval.py task=open_drawer snapshot=checkpoints/open_drawer.pt1@misc{dai2026skipskiprefineefficient,
2 title={SkiP: When to Skip and When to Refine for Efficient Robot Manipulation},
3 author={Mingtong Dai and Guanqi Peng and Yongjie Bai and Feng Yan and Chunjie Chen and Lingbo Liu and Liang Lin and Xinyu Wu},
4 year={2026},
5 eprint={2605.15536},
6 archivePrefix={arXiv},
7 primaryClass={cs.RO},
8 url={https://arxiv.org/abs/2605.15536},
9}