admin/lerobot
1
0
Fork 0
mirror of https://github.com/huggingface/lerobot.git synced 2026-05-22 12:09:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

update doc

Browse Source
This commit is contained in:
Jade Choghari
2025-09-02 08:12:10 -04:00
parent e91a773b93
commit 7b556079d8
1 changed files with 33 additions and 26 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/source/libero.mdx
+33 -26
View File
@@ -67,46 +67,53 @@ python src/lerobot/scripts/eval.py \
When using LIBERO through LeRobot, policies interact with the environment via **observations** and **actions**: When using LIBERO through LeRobot, policies interact with the environment via **observations** and **actions**:
- **Observations** - **Observations**
- `observation.state` – proprioceptive features (agent state). - `observation.state` – proprioceptive features (agent state).
- `observation.images.image` – main camera view (`agentview_image`). - `observation.images.image` – main camera view (`agentview_image`).
- `observation.images.image2` – wrist camera view (`robot0_eye_in_hand_image`). - `observation.images.image2` – wrist camera view (`robot0_eye_in_hand_image`).
⚠️ **Note:** LeRobot enforces the `.images.*` prefix for any visual features. Make sure your dataset metadata keys match this convention when evaluating. ⚠️ **Note:** LeRobot enforces the `.images.*` prefix for any visual features. Make sure your dataset metadata keys match this convention when evaluating.
- **Actions** - **Actions**
- Continuous control values in a `Box(-1, 1, shape=(7,))` space. - Continuous control values in a `Box(-1, 1, shape=(7,))` space.
We also provide a notebook for quick testing: We also provide a notebook for quick testing:
Training with LIBERO Training with LIBERO
## Training with LIBERO
When training on LIBERO tasks, make sure your dataset parquet and metadata keys follow the LeRobot convention. When training on LIBERO tasks, make sure your dataset parquet and metadata keys follow the LeRobot convention.
The environment expects: The environment expects:
observation.state → 8-dim agent state - `observation.state` → 8-dim agent state
- `observation.images.image` → main camera (`agentview_image`)
- `observation.images.image2` → wrist camera (`robot0_eye_in_hand_image`)
observation.images.image → main camera (agentview_image) ⚠️ Cleaning the dataset upfront is **cleaner and more efficient** than remapping keys inside the code. We plan to provide a script to easily preprocess such data.
observation.images.image2 → wrist camera (robot0_eye_in_hand_image) ---
⚠️ Cleaning the dataset upfront is cleaner and more efficient than remapping keys inside the code. We plan to provide a script to easily preprocess such data. ### Example training command
Example training command ```bash
python src/lerobot/scripts/train.py \ python src/lerobot/scripts/train.py \
--policy.type=smolvla \ --policy.type=smolvla \
--dataset.repo_id=jadechoghari/smol-libero3 \ --dataset.repo_id=jadechoghari/smol-libero3 \
--env.type=libero \ --env.type=libero \
--env.task=libero_10,libero_spatial \ --env.task=libero_10,libero_spatial \
--output_dir=./outputs/ \ --output_dir=./outputs/ \
--steps=100000 \ --steps=100000 \
--batch_size=4 \ --batch_size=4 \
--env.multitask_eval=True \ --env.multitask_eval=True \
--eval.batch_size=1 \ --eval.batch_size=1 \
--eval.n_episodes=1 --eval.n_episodes=1
```
Note on rendering ---
### Note on rendering
LeRobot uses MuJoCo for simulation. You need to set the rendering backend before training or evaluation: LeRobot uses MuJoCo for simulation. You need to set the rendering backend before training or evaluation:
export MUJOCO_GL=egl → for headless servers (e.g. HPC, cloud) - `export MUJOCO_GL=egl` → for headless servers (e.g. HPC, cloud)
- `export MUJOCO_GL=glfw` → for local runs with a display
export MUJOCO_GL=glfw → for local runs with a display