Skip to content
RobothecaBeta
Log in

robomimic

  • Software
  • Humanoids and robot learning
  • Framework

A framework for robot learning from demonstration, offering datasets of robot manipulation demonstrations and offline learning algorithms to train policies from them.

Made by ARISE Initiative.

Source on GitHub: github.com/ARISE-Initiative/robomimic (opens in a new tab). Facts read at commit d309eae (opens in a new tab).

Licenses

Code
MIT (opens in a new tab)

Read by Robotheca from LICENSE (opens in a new tab) (MIT) at commit d309eae (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Provides a broad set of demonstration datasets collected on robot manipulation domains.
  • Includes offline learning algorithms that learn robot behavior from these demonstration datasets.
  • Aims to make robot learning accessible and reproducible, so tasks and algorithms can be benchmarked fairly.
  • Offers a Colab quickstart demo that runs without a local installation.
  • Includes a Dockerfile that builds an environment with Python 3.9, Miniconda, robosuite, and PyTorch, with CPU or GPU support.
  • Supports reproducing results from different benchmarks and datasets, with dataset download instructions in its documentation.

Written by Robotheca from the project's README (opens in a new tab) at commit d309eae.

Getting started

Difficulty
Intermediate
Hardware it needs, as the project states it
Docker environment runs on CPU only, or with GPU if available using the --gpus all flag; no other hardware requirements are stated.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
10 Aug 2026 on master
Latest release
v0.5 (27 Jun 2025)

Checked on GitHub on 16 Oct 2026.

Links

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.