| --- |
| license: mit |
| datasets: |
| - lerobot/pusht_image |
| tags: |
| - lerobot |
| - pusht |
| - diffusion |
| --- |
| |
| # Model Card for Mini Diffusion Policy / PushT |
|
|
| We add few lines to add an extra level-2 minibatch for Diffusion Policy (as per [Mini Diffuser (ICRA 2026)](https://arxiv.org/abs/2505.09430)) trained for the `PushT` environment from [gym-pusht](https://github.com/huggingface/gym-pusht). This enables tens of equivalent batch size per gradient step, and end up saving at least 60% of the training time to obtain similar training results. |
|
|
| ## How to Get Started with the Model |
|
|
| See the [LeRobot library](https://github.com/huggingface/lerobot) for instructions on how to load and evaluate this model. |
|
|
| ## Training Details |
|
|
| Trained with a forked [LeRobot@ |
| 7bd533a](https://github.com/utomm/lerobot/tree/minidp-0.4.2). |
|
|
| The model was trained using [LeRobot's training script](https://github.com/huggingface/lerobot/blob/main/lerobot/scripts/train.py) and with the [pusht](https://huggingface.co/datasets/lerobot/pusht) dataset, using this command: |
|
|
| ```bash |
| lerobot-train --policy.type=minidiffusion --dataset.repo_id=lerobot/pusht_image\ |
| --env.type=pusht --seed=100000 --batch_size=32 --log_freq=200 --wandb.disable_artifact=true\ |
| --steps=100000 --eval_freq=10000 --save_freq=10000 --wandb.enable=true --policy.repo_id=id\ |
| --wandb.project=minidp --policy.push_to_hub=false --policy.level2_batch_size=8 --job_name=minidp-32-8 |
| ``` |
|
|
|
|
| The training curves, and the comparasions with original DP may be found at https://api.wandb.ai/links/hu2240877635/defcr4wu |
| <iframe src="https://wandb.ai/hu2240877635/minidp/reports/Accelerating-Diffusion-Policy-Training-with-MiniDP--VmlldzoxNjI1NzQ0OA" style="border:none;height:1024px;width:100%"> |
| The current model corresponds to the checkpoint at 90k steps. |
