The current project retains a version history rather than treating every release as interchangeable. An evaluation-horizon increase in v1.0.1 changes how much time a policy receives to finish tasks.
RoboCasa365 research team · Publication date not disclosed · Source accessed 2026-09-28
Reading results
Training data, scene split, horizon and environment version should accompany all scores. Using the same policy checkpoint with a longer episode limit can change success without changing the model.
robocasa · 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
Original RoboCasa and RoboCasa365 are separate benchmark scopes. Kitchen simulation is not a physical deployment claim.
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.
robocasa · Repository · Publication date not disclosed · Source accessed 2026-09-28
License: MIT code; CC BY 4.0 assets and datasets stated by project. 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.