Offline robot-learning framework

robomimic

robomimic provides algorithms and workflows for learning manipulation policies from demonstration datasets.

Source contextPrimary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Reviewed recordLast reviewed 1 sources ↗5 sourced fields

Role in the stack

The framework separates dataset handling, policy training and evaluation. Recent release notes include diffusion policies, language-conditioned workflows and multiple datasets, which should be tied to a specific release.

Source contextPrimary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Integration decision

It integrates with robosuite environments and their data collection conventions. A result must preserve the dataset, observation specification and algorithm configuration rather than attributing one score to the framework.

Source contextPrimary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Operational and reuse limits

Offline learning quality depends on demonstrations and evaluation distribution. Framework access is not evidence that a policy works on an untested robot.

Source contextPrimary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Infrastructure profile

Developer
ARISE Initiative
Primary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Category
Offline robot-learning framework
Primary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Exact version / scope
Not publicly disclosed
Environment
Not publicly disclosed
Access model
Public reference code and research resources
Primary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

License
Not publicly disclosed

Engineering fit

Task scope
Not publicly disclosed
Compute
Not publicly disclosed
Integrations
Not publicly disclosed
Pricing / access
Not publicly disclosed

Additional disclosed fields

Inputs
Demonstration datasets and training configuration
Primary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Outputs
Learned policies and evaluation artifacts
Primary specReviewed
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

What this evidence does not establish

  • Offline learning quality depends on demonstrations and evaluation distribution. Framework access is not evidence that a policy works on an untested robot.

Relationships & deployments

Related reading is an editorial crosslink. Sourced connections describe relationships reported in the cited material. A link to a versioned profile does not establish compatibility with that version unless the connection note explicitly identifies it.

compatible with
robomimic → robosuite
Sources 1
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Publication date not disclosed · Source accessed 2026-09-28

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.

Connection reviewed 2026-09-28

Record history & verified changes

A research review records when we checked a source. It does not mark a product launch or a new deployment.

Initial reviewed record. No subsequent field change has been recorded.

Inspect the evidence

Sources & evidence

md-robomimic
ARISE-Initiative/robomimic official repository

ARISE-Initiative · Repository · Publication date not disclosed · Source accessed 2026-09-28

Factual summary and attribution only; no upstream prose, images, weights, or dataset redistributed.

Official README inspected live. Repository code terms do not automatically cover model weights, data, or third-party assets.