Benchmark / simulation

Kinetix

Kinetix is a JAX-based physics environment for studying generalization across procedurally generated control problems.

Source contextPrimary specReviewed
Sources 2
FLAIROx/Kinetix official repository

FLAIROx · 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.

Kinetix original evaluation paper

Kinetix research team · Publication date not disclosed · Source accessed 2026-09-28

Reviewed recordLast reviewed 3 sources ↗6 sourced fields

What the protocol tests

Agents actuate motors and thrusters in constructed physical puzzles. The task structure centers on reaching a target contact while avoiding failure contacts; it does not assume a human-shaped robot.

Source contextPrimary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Reading results

Training distributions and held-out level collections determine what generalization means. An adapter result on Kinetix concerns delayed control in this environment, not a direct manipulation score for a physical arm.

Source contextPrimary specReviewed
Sources 2
FLAIROx/Kinetix official repository

FLAIROx · 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.

Kinetix original evaluation paper

Kinetix research team · Publication date not disclosed · Source accessed 2026-09-28

Methodology and reuse limits

Abstract physics-control success cannot be ranked against robot manipulation success on a shared numerical scale.

Source contextPrimary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Evaluation protocol

Exact version / scope
Kinetix procedurally generated physics environments
Primary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Environment
simulation
Primary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Metric definition
Solve rate on handmade held-out levels
Primary specReviewed
Sources 1
Kinetix original evaluation paper

Kinetix research team · Publication date not disclosed · Source accessed 2026-09-28

Task scope
Not publicly disclosed
Embodiment
Abstract two-dimensional rigid-body systems
Primary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Access & reuse

Access model
Public research documentation and evaluation resources
Primary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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

Additional disclosed fields

Category
Robot evaluation benchmark
Primary specReviewed
Sources 1
FLAIROx/Kinetix official repository

FLAIROx · 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.

Reported benchmark results

Context before scores. Results from different benchmarks are not directly comparable. A simulation result does not establish real-world reliability, safety or commercial availability.
No result meets our complete revision and methodology requirements for this record yet. Inspect the original benchmark documentation before comparing published scores.

What this evidence does not establish

  • Abstract physics-control success cannot be ranked against robot manipulation success on a shared numerical scale.

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.

evaluated on
Action ControlNet (ACNet) → Kinetix
Sources 1
ActionControlNet original paper

Tiecheng Guo and Meng Guo · Published 2026-06-24 · Source accessed 2026-09-28

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-kinetix
FLAIROx/Kinetix official repository

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

License: MIT code. 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.

md-kinetix-paper
Kinetix original evaluation paper

Kinetix research team · Paper · Publication date not disclosed · Source accessed 2026-09-28

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