README.md

---
datasets: HuggingFaceVLA/libero
library_name: lerobot
license: apache-2.0
model_name: diffusion
pipeline_tag: robotics
tags:
- lerobot
- diffusion
- robotics
---

# Diffusion Policy — LIBERO single-task (book → caddy)

[Diffusion Policy](https://huggingface.co/papers/2303.04137) trained with
[LeRobot](https://github.com/huggingface/lerobot) on **one LIBERO task**:

> *pick up the book and place it in the back compartment of the caddy*

Trained from scratch on a laptop GPU (RTX 4050, 6 GB VRAM).

## Evaluation

Evaluated in the LIBERO simulator (`libero_10`, task 5) — the same task the
policy was trained on. All 10 rollouts use LIBERO's canonical initial states
with randomised object poses.

| Task | Suite | Trials | Successes | Success rate |
| ---- | ----- | ------ | --------- | ------------ |
| pick up the book and place it in the back compartment of the caddy | libero_10 task 5 | 10 | 6 | **60%** |

Per-episode outcomes (1 = success): `[1, 0, 1, 1, 0, 1, 1, 0, 1, 0]`

Reproduce:
```bash
lerobot-eval \
  --policy.path=anuragbhandari-eng/diffusion_libero_object \
  --env.type=libero --env.task=libero_10 --env.task_ids="[5]" \
  --env.observation_height=256 --env.observation_width=256 \
  --eval.n_episodes=10 --eval.batch_size=1 --env.max_parallel_tasks=1 \
  --output_dir=eval_out
```

---

## Model Details

- **License:** apache-2.0
- **Robot type:** `panda` (Franka)
- **Cameras:** agentview (`image`) + wrist (`image2`)

## Inputs & Outputs

**Inputs**

| Feature | Type | Shape |
| --- | --- | --- |
| `observation.images.image` | VISUAL | `(3, 256, 256)` |
| `observation.images.image2` | VISUAL | `(3, 256, 256)` |
| `observation.state` | STATE | `(8,)` |

**Outputs**

| Feature | Type | Shape |
| --- | --- | --- |
| `action` | ACTION | `(7,)` |

## Training Dataset

- **Repository:** [HuggingFaceVLA/libero](https://huggingface.co/datasets/HuggingFaceVLA/libero)
- **Task:** `pick up the book and place it in the back compartment of the caddy`
- **Episodes used:** 19 (episodes 27,28,47,55,61,64,81,103,104,109,111,127,133,136,141,147,154,158,159)
- **Frames:** 3 609
- **Frame rate:** 10.0 FPS

## Training Configuration

| Setting | Value |
| --- | --- |
| Training steps | 80 000 |
| Batch size | 8 |
| Optimizer | adam |
| Learning rate | 0.0001 |
| Seed | 1000 |
| Hardware | RTX 4050 Laptop 6 GB VRAM |
| LeRobot version | 0.5.2 |

---

## How to Reproduce Training

```bash
pip install -e ".[libero]" --no-build-isolation
export MUJOCO_GL=egl
lerobot-train \
  --policy.type=diffusion \
  --dataset.repo_id=HuggingFaceVLA/libero \
  --dataset.episodes="[27,28,47,55,61,64,81,103,104,109,111,127,133,136,141,147,154,158,159]" \
  --batch_size=8 --steps=80000 \
  --policy.device=cuda \
  --policy.push_to_hub=true \
  --policy.repo_id=anuragbhandari-eng/diffusion_libero_object \
  --save_freq=5000
```

---

## Citation

```bibtex
@misc{cadene2024lerobot,
    author = {Cadene, Remi and others},
    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
    howpublished = "\url{https://github.com/huggingface/lerobot}",
    year = {2024}
}
```