Merge remote-tracking branch 'upstream/main'

Author: EAOZONE

.github/workflows/release.yml

@@ -19,6 +19,11 @@ on:
     tags:
       - 'v*.*.*' # Trigger on tags like v0.1.0, v1.0.0
 
+# Sets up the environment variables
+env:
+  UV_VERSION: "0.8.0"
+  PYTHON_VERSION: "3.10"
+
 jobs:
   # This job builds the Python package and publishes it to PyPI
   build-and-publish:
@@ -50,6 +55,7 @@ jobs:
           VERSION_NUMBER=${VERSION#v}
           echo "tag_version=$VERSION_NUMBER" >> $GITHUB_OUTPUT
       - name: Check if version matches pyproject.toml
+        if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
         # zizmor: ignore[template-injection]
         run: |
           TAG_VERSION=${{ steps.extract_info.outputs.tag_version }}
@@ -86,13 +92,29 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         # zizmor: ignore[template-injection]
-        run: gh release create ${{ github.ref_name }} --release-name "Release ${{ github.ref_name }}" --generate-notes ./dist/*
+        run: |
+          gh release create ${{ github.ref_name }} \
+            --title "Release ${{ github.ref_name }}" \
+            --generate-notes \
+            --draft=$([[ "${{ github.ref_name }}" == *-* ]] && echo true || echo false) \
+            --prerelease=$([[ "${{ github.ref_name }}" == *-* ]] && echo true || echo false) \
+            ./dist/*
+
+      - name: Publish to TestPyPI for pre-releases
+        # True for tags like 'v0.2.0-rc1'
+        if: startsWith(github.ref, 'refs/tags/v') && contains(github.ref, '-')
+        uses: pypa/gh-action-pypi-publish@v1.12.4 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          verbose: true
+          print-hash: true
 
       - name: Publish to PyPI
-        if: startsWith(github.ref, 'refs/tags/v')
+        if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
         uses: pypa/gh-action-pypi-publish@v1.12.4 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
         with:
-          password: ${{ secrets.PYPI_API_TOKEN }}
+          verbose: true
+          print-hash: true
 
   # This job runs end-to-end tests on the release
   test-release:
@@ -119,15 +141,31 @@ jobs:
           enable-cache: true
           version: ${{ env.UV_VERSION }}
           python-version: ${{ env.PYTHON_VERSION }}
+      - name: Create uv virtual environment
+        run: uv venv
       - name: Install lerobot release
-        run: uv run pip install lerobot==${{ needs.build-and-publish.outputs.version }} # zizmor: ignore[template-injection]
-
+        # zizmor: ignore[template-injection]
+        run: |
+          VERSION="${{ needs.build-and-publish.outputs.version }}"
+          if [[ "$VERSION" == *-* ]]; then
+            BASE_VERSION="${VERSION%%-*}"
+            echo "Installing pre-release version $BASE_VERSION from TestPyPI..."
+            uv pip install \
+              --index-url https://test.pypi.org/simple/ \
+              --extra-index-url https://pypi.org/simple \
+              --index-strategy unsafe-best-match \
+               "lerobot[all]==$BASE_VERSION"
+          else
+            echo "Installing release version $VERSION from PyPI..."
+            uv pip install "lerobot[all]==$VERSION"
+          fi
       - name: Check lerobot version
-        run: uv run lerobot --version
+        run: uv run python -c "import lerobot; print(lerobot.__version__)"
 
       - name: Run end-to-end tests
         run: uv run make test-end-to-end
 
 
-# TODO(Steven): Publish draft/pre-release and to test pypi
+# TODO(Steven): Publish draft/pre-release and to test pypi weekly
+# TODO(Steven): Separate build and publish job
 # TODO(Steven): Tag documentation with the same version as the package

README.md

@@ -0,0 +1,3 @@
+# docs-requirements.txt
+hf-doc-builder @ git+https://github.com/huggingface/doc-builder.git@main
+watchdog>=6.0.0

docs-requirements.txt

@@ -20,7 +20,7 @@ To generate the documentation, you first have to build it. Several packages are
 you can install them with the following command, at the root of the code repository:
 
 ```bash
-pip install -e ".[docs]"
+pip install -e . -r docs-requirements.txt
 ```
 
 You will also need `nodejs`. Please refer to their [installation page](https://nodejs.org/en/download)

docs/README.md

@@ -294,7 +294,7 @@ dataset.push_to_hub()
 
 #### Dataset upload
 
-Locally, your dataset is stored in this folder: `~/.cache/huggingface/lerobot/{repo-id}`. At the end of data recording, your dataset will be uploaded on your Hugging Face page (e.g. https://huggingface.co/datasets/cadene/so101_test) that you can obtain by running:
+Locally, your dataset is stored in this folder: `~/.cache/huggingface/lerobot/{repo-id}`. At the end of data recording, your dataset will be uploaded on your Hugging Face page (e.g. `https://huggingface.co/datasets/${HF_USER}/so101_test`) that you can obtain by running:
 
 ```bash
 echo https://huggingface.co/datasets/${HF_USER}/so101_test
@@ -428,7 +428,7 @@ Your robot should replicate movements similar to those you recorded. For example
 
 ## Train a policy
 
-To train a policy to control your robot, use the [`python -m lerobot.scripts.train`](../src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
+To train a policy to control your robot, use the [`python -m lerobot.scripts.train`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
 
 ```bash
 python -m lerobot.scripts.train \
@@ -444,7 +444,7 @@ python -m lerobot.scripts.train \
 Let's explain the command:
 
 1. We provided the dataset as argument with `--dataset.repo_id=${HF_USER}/so101_test`.
-2. We provided the policy with `policy.type=act`. This loads configurations from [`configuration_act.py`](../src/lerobot/policies/act/configuration_act.py). Importantly, this policy will automatically adapt to the number of motor states, motor actions and cameras of your robot (e.g. `laptop` and `phone`) which have been saved in your dataset.
+2. We provided the policy with `policy.type=act`. This loads configurations from [`configuration_act.py`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/act/configuration_act.py). Importantly, this policy will automatically adapt to the number of motor states, motor actions and cameras of your robot (e.g. `laptop` and `phone`) which have been saved in your dataset.
 3. We provided `policy.device=cuda` since we are training on a Nvidia GPU, but you could use `policy.device=mps` to train on Apple silicon.
 4. We provided `wandb.enable=true` to use [Weights and Biases](https://docs.wandb.ai/quickstart) for visualizing training plots. This is optional but if you use it, make sure you are logged in by running `wandb login`.
 
@@ -462,9 +462,9 @@ If you do not want to push your model to the hub after training use `--policy.pu
 
 Additionally you can provide extra `tags` or specify a `license` for your model or make the model repo `private` by adding this: `--policy.private=true --policy.tags=\[ppo,rl\] --policy.license=mit`
 
-#### Train using Collab
+#### Train using Google Colab
 
-If your local computer doesn't have a powerful GPU you could utilize Google Collab to train your model by following the [ACT training notebook](./notebooks#training-act).
+If your local computer doesn't have a powerful GPU you could utilize Google Colab to train your model by following the [ACT training notebook](./notebooks#training-act).
 
 #### Upload policy checkpoints
 

docs/source/il_robots.mdx

@@ -96,7 +96,7 @@ If you uploaded your dataset to the hub you can [visualize your dataset online](
 
 ## Train a policy
 
-To train a policy to control your robot, use the [`python -m lerobot.scripts.train`](../src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
+To train a policy to control your robot, use the [`python -m lerobot.scripts.train`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
 
 ```bash
 python -m lerobot.scripts.train \
@@ -111,7 +111,7 @@ python -m lerobot.scripts.train \
 Let's explain the command:
 
 1. We provided the dataset as argument with `--dataset.repo_id=${HF_USER}/il_gym`.
-2. We provided the policy with `policy.type=act`. This loads configurations from [`configuration_act.py`](../src/lerobot/policies/act/configuration_act.py). Importantly, this policy will automatically adapt to the number of motor states, motor actions and cameras of your robot (e.g. `laptop` and `phone`) which have been saved in your dataset.
+2. We provided the policy with `policy.type=act`. This loads configurations from [`configuration_act.py`](https://github.com/huggingface/lerobot/blob/main/src/lerobot/policies/act/configuration_act.py). Importantly, this policy will automatically adapt to the number of motor states, motor actions and cameras of your robot (e.g. `laptop` and `phone`) which have been saved in your dataset.
 3. We provided `policy.device=cuda` since we are training on a Nvidia GPU, but you could use `policy.device=mps` to train on Apple silicon.
 4. We provided `wandb.enable=true` to use [Weights and Biases](https://docs.wandb.ai/quickstart) for visualizing training plots. This is optional but if you use it, make sure you are logged in by running `wandb login`.
 

docs/source/il_sim.mdx

@@ -0,0 +1,14 @@
+## Paper
+
+https://tonyzhaozh.github.io/aloha
+
+## Citation
+
+```bibtex
+@article{zhao2023learning,
+  title={Learning fine-grained bimanual manipulation with low-cost hardware},
+  author={Zhao, Tony Z and Kumar, Vikash and Levine, Sergey and Finn, Chelsea},
+  journal={arXiv preprint arXiv:2304.13705},
+  year={2023}
+}
+```

docs/source/policy_act_README.md

@@ -0,0 +1,14 @@
+## Paper
+
+https://diffusion-policy.cs.columbia.edu
+
+## Citation
+
+```bibtex
+@article{chi2024diffusionpolicy,
+	author = {Cheng Chi and Zhenjia Xu and Siyuan Feng and Eric Cousineau and Yilun Du and Benjamin Burchfiel and Russ Tedrake and Shuran Song},
+	title ={Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},
+	journal = {The International Journal of Robotics Research},
+	year = {2024},
+}
+```

docs/source/policy_diffusion_README.md

@@ -0,0 +1,14 @@
+## Paper
+
+https://arxiv.org/abs/2506.01844
+
+## Citation
+
+```bibtex
+@article{shukor2025smolvla,
+  title={SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics},
+  author={Shukor, Mustafa and Aubakirova, Dana and Capuano, Francesco and Kooijmans, Pepijn and Palma, Steven and Zouitine, Adil and Aractingi, Michel and Pascal, Caroline and Russi, Martino and Marafioti, Andres and Alibert, Simon and Cord, Matthieu and Wolf, Thomas and Cadene, Remi},
+  journal={arXiv preprint arXiv:2506.01844},
+  year={2025}
+}
+```

docs/source/policy_smolvla_README.md

@@ -0,0 +1,14 @@
+## Paper
+
+https://www.nicklashansen.com/td-mpc/
+
+## Citation
+
+```bibtex
+@inproceedings{Hansen2022tdmpc,
+	title={Temporal Difference Learning for Model Predictive Control},
+	author={Nicklas Hansen and Xiaolong Wang and Hao Su},
+	booktitle={ICML},
+	year={2022}
+}
+```