Instructions to use LUC1O/act-5090-C3_transfer_cube_scripted with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use LUC1O/act-5090-C3_transfer_cube_scripted with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
|
Download README.md from LUC1O/act-5090-C3_transfer_cube_scripted: direct link, hf CLI and curl.
- Browser
- Download file 729 Bytes
-
https://huggingface.co/LUC1O/act-5090-C3_transfer_cube_scripted/resolve/main/README.md
- Command line
-
hf download hf://LUC1O/act-5090-C3_transfer_cube_scripted/README.md
-
curl -L -o README.md https://huggingface.co/LUC1O/act-5090-C3_transfer_cube_scripted/resolve/main/README.md
729 Bytes
metadata
library_name: lerobot
tags:
- lerobot
- act
- robotics
- aloha
datasets:
- lerobot/aloha_sim_transfer_cube_scripted
ACT — C3_transfer_cube_scripted
ACT trained with LeRobot (ba83e4c, official ACT hyperparameters: batch 8, lr 1e-5, chunk 100, 100k steps) on one RTX 5090.
- Dataset:
lerobot/aloha_sim_transfer_cube_scripted - Eval:
aloha/AlohaTransferCube-v0, 200 episodes → 93.0% success (186/200, 95% Wilson CI 88.6–95.8) - Full benchmark, logs and reproduction scripts: https://github.com/Jerryisqx/ACT-5090-benchmark
lerobot-eval --policy.path=LUC1O/act-5090-C3_transfer_cube_scripted --env.type=aloha --env.task=AlohaTransferCube-v0 --eval.n_episodes=50 --eval.use_async_envs=false