LeRobot Diffusion Policy PushT closed-loop evaluation: robotics skill example

LeRobot Diffusion Policy PushT closed-loop evaluation. Source-pinned, bounded simulation with explicit goal checks; no physical execution.

Markdown | JSON example and evidence | Canonical contract | All examples

Task and environment

lerobot | 0.3.3 | pusht-2d-pusher | diffusion_policy | linux | 3.10

Example input

{
  "seed": 0
}

Retrieve without installation

curl -fsSL 'https://api.superfastrobotics.com/v1/skills/lerobot-diffusion-pusht?hub_commit=ce1d44c01f1a9f707f055da0888068fe32390e62&record_version=1.0.0&include=experience'

Inspect source, license, environment and execution evidence before preparing. Preparation and execution are separate actions.

Success condition

All declared goal and finite-state checks pass; exit 0 with task_complete. Original PushT success flag and measured object/target overlap >=95%; no accuracy claim beyond the three retained seed episodes. Checkpoint license: Apache-2.0, preserved at its immutable model revision.

Recorded evidence

import_verified: 1/3 frozen cases completed; retained failures are not promoted.

Source commit: b883328e6c95681ca90a18b102e4ae5e1f91e2bf. Record version: 1.0.0. This page performs no execution.