metadata
license: apache-2.0
library_name: lerobot
tags:
- lerobot
- diffusion-policy
- imitation-learning
- robotics
- ur3e
- bimanual
datasets:
- WetLabRoboData/lerobot-data-multitask_12task_mix
pipeline_tag: robotics
diffusion-multitask_12task_mix-multitask
LeRobot diffusion policy for the multitask_12task_mix task.
| Field | Value |
|---|---|
| Policy family | diffusion (LeRobot) |
| Variant | Multitask pretrain (trained on the 12-task mix of 1206 episodes) |
| Training dataset | WetLabRoboData/lerobot-data-multitask_12task_mix |
| Target task | multitask_12task_mix | | Eval episodes | 0 | | Eval successes | 0 / 0 | | Robot | UR3e bimanual (3 cameras) |
Evaluation
Rollout videos + per-episode outcomes: WetLabRoboData/eval-diffusion-multitask_12task_mix-multitask.
Load and deploy
from lerobot.policies.diffusion.modeling_diffusion import DiffusionPolicy
policy = DiffusionPolicy.from_pretrained("WetLabRoboData/diffusion-multitask_12task_mix-multitask")
Provenance
Reorganized from WetLabRoboData/lerobot-data-rama-lbm_pretrain_all_ds5 on 2026-10-04. The archived
training outputs (checkpoints, train_config.json, wandb/) are preserved in
the old/ subfolder of that source repo for traceability.