MarkFzp/act-plus-plus
Imitation learning framework implementing ACT, Diffusion Policy, and VINN algorithms for training policies on the Mobile ALOHA robotic system.
Not currently ranked — collecting fresh signals.
star history
This repository provides implementations of several imitation learning algorithms for robotic manipulation, including Action Chunking with Transformers (ACT), Diffusion Policy, and VINN. It includes simulated environments (Transfer Cube and Bimanual Insertion) built with Mujoco and DM-Control for training and evaluation. The models use DETR-based architectures for transformer-based action chunking and diffusion-based policy learning.
Frequently asked
- What is MarkFzp/act-plus-plus?
- Imitation learning framework implementing ACT, Diffusion Policy, and VINN algorithms for training policies on the Mobile ALOHA robotic system.
- Is act-plus-plus open source?
- Yes — MarkFzp/act-plus-plus is open source, released under the MIT license.
- What language is act-plus-plus written in?
- MarkFzp/act-plus-plus is primarily written in Python.
- How popular is act-plus-plus?
- MarkFzp/act-plus-plus has 3.6k stars on GitHub.
- Where can I find act-plus-plus?
- MarkFzp/act-plus-plus is on GitHub at https://github.com/MarkFzp/act-plus-plus.