---
license: bsd-2-clause
---
# Action Chunking with Transformers (ACT)

The model was trained with the [MujocoUR5eCable dataset](https://huggingface.co/datasets/RoboManipBaselines/MujocoUR5eCable).

## Install
See [GitHub](https://github.com/isri-aist/RoboManipBaselines/blob/master/doc/install.md#ACT) for installation.

## Policy rollout
Run a trained policy:
```console
# Go to the top directory of this repository
$ cd robo_manip_baselines
$ python ./bin/Rollout.py Act MujocoUR5eCable --checkpoint ./checkpoint/Act/<checkpoint_name>/policy_last.ckpt
```

## Technical Details
For more information on the technical details, please see the following paper:
```bib
@INPROCEEDINGS{ACT_RSS23,
  author = {Tony Z. Zhao and Vikash Kumar and Sergey Levine and Chelsea Finn},
  title = {Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2023},
  month = {July},
  doi = {10.15607/RSS.2023.XIX.016}
}
```

## RoboManipBaselines Paper
https://huggingface.co/papers/2509.17057