format docs

for more information, see https://pre-commit.ci

.github/PULL_REQUEST_TEMPLATE.md

@@ -30,7 +30,7 @@ pytest -sx tests/test_stuff.py::test_something
 ```
 
 ```bash
-lerobot-train --some.option=true
+python -m lerobot.scripts.train --some.option=true
 ```
 
 ## SECTION TO REMOVE BEFORE SUBMITTING YOUR PR

.github/workflows/nightly.yml

@@ -29,8 +29,8 @@ on:
 env:
   UV_VERSION: "0.8.0"
   PYTHON_VERSION: "3.10"
-  DOCKER_IMAGE_NAME_CPU: huggingface/lerobot-cpu:latest
-  DOCKER_IMAGE_NAME_GPU: huggingface/lerobot-gpu:latest
+  DOCKER_IMAGE_NAME_CPU: huggingface/lerobot-gpu:latest
+  DOCKER_IMAGE_NAME_GPU: huggingface/lerobot-cpu:latest
 
 # Ensures that only the latest commit is built, canceling older runs.
 concurrency:

.github/workflows/release.yml

@@ -19,11 +19,6 @@ 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:
@@ -55,7 +50,6 @@ 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 }}
@@ -92,29 +86,13 @@ jobs:
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
         # zizmor: ignore[template-injection]
-        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
+        run: gh release create ${{ github.ref_name }} --release-name "Release ${{ github.ref_name }}" --generate-notes ./dist/*
 
       - name: Publish to PyPI
-        if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
+        if: startsWith(github.ref, 'refs/tags/v')
         uses: pypa/gh-action-pypi-publish@v1.12.4 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
         with:
-          verbose: true
-          print-hash: true
+          password: ${{ secrets.PYPI_API_TOKEN }}
 
   # This job runs end-to-end tests on the release
   test-release:
@@ -141,31 +119,15 @@ jobs:
           enable-cache: true
           version: ${{ env.UV_VERSION }}
           python-version: ${{ env.PYTHON_VERSION }}
-      - name: Create uv virtual environment
-        run: uv venv
       - name: Install lerobot release
-        # zizmor: ignore[template-injection]
-        run: |
-          VERSION="${{ 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
+        run: uv run pip install lerobot==${{ needs.build-and-publish.outputs.version }} # zizmor: ignore[template-injection]
+
       - name: Check lerobot version
-        run: uv run python -c "import lerobot; print(lerobot.__version__)"
+        run: uv run 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 weekly
-# TODO(Steven): Separate build and publish job
+# TODO(Steven): Publish draft/pre-release and to test pypi
 # TODO(Steven): Tag documentation with the same version as the package

Makefile

@@ -44,7 +44,7 @@ test-end-to-end:
 	${MAKE} DEVICE=$(DEVICE) test-smolvla-ete-eval
 
 test-act-ete-train:
-	lerobot-train \
+	python -m lerobot.scripts.train \
 		--policy.type=act \
 		--policy.dim_model=64 \
 		--policy.n_action_steps=20 \
@@ -68,12 +68,12 @@ test-act-ete-train:
 		--output_dir=tests/outputs/act/
 
 test-act-ete-train-resume:
-	lerobot-train \
+	python -m lerobot.scripts.train \
 		--config_path=tests/outputs/act/checkpoints/000002/pretrained_model/train_config.json \
 		--resume=true
 
 test-act-ete-eval:
-	lerobot-eval \
+	python -m lerobot.scripts.eval \
 		--policy.path=tests/outputs/act/checkpoints/000004/pretrained_model \
 		--policy.device=$(DEVICE) \
 		--env.type=aloha \
@@ -82,7 +82,7 @@ test-act-ete-eval:
 		--eval.batch_size=1
 
 test-diffusion-ete-train:
-	lerobot-train \
+	python -m lerobot.scripts.train \
 		--policy.type=diffusion \
 		--policy.down_dims='[64,128,256]' \
 		--policy.diffusion_step_embed_dim=32 \
@@ -106,7 +106,7 @@ test-diffusion-ete-train:
 		--output_dir=tests/outputs/diffusion/
 
 test-diffusion-ete-eval:
-	lerobot-eval \
+	python -m lerobot.scripts.eval \
 		--policy.path=tests/outputs/diffusion/checkpoints/000002/pretrained_model \
 		--policy.device=$(DEVICE) \
 		--env.type=pusht \
@@ -115,7 +115,7 @@ test-diffusion-ete-eval:
 		--eval.batch_size=1
 
 test-tdmpc-ete-train:
-	lerobot-train \
+	python -m lerobot.scripts.train \
 		--policy.type=tdmpc \
 		--policy.device=$(DEVICE) \
 		--policy.push_to_hub=false \
@@ -137,7 +137,7 @@ test-tdmpc-ete-train:
 		--output_dir=tests/outputs/tdmpc/
 
 test-tdmpc-ete-eval:
-	lerobot-eval \
+	python -m lerobot.scripts.eval \
 		--policy.path=tests/outputs/tdmpc/checkpoints/000002/pretrained_model \
 		--policy.device=$(DEVICE) \
 		--env.type=xarm \
@@ -148,7 +148,7 @@ test-tdmpc-ete-eval:
 
 
 test-smolvla-ete-train:
-	lerobot-train \
+	python -m lerobot.scripts.train \
 		--policy.type=smolvla \
 		--policy.n_action_steps=20 \
 		--policy.chunk_size=20 \
@@ -171,7 +171,7 @@ test-smolvla-ete-train:
 		--output_dir=tests/outputs/smolvla/
 
 test-smolvla-ete-eval:
-	lerobot-eval \
+	python -m lerobot.scripts.eval \
 		--policy.path=tests/outputs/smolvla/checkpoints/000004/pretrained_model \
 		--policy.device=$(DEVICE) \
 		--env.type=aloha \

README.md

@@ -1,21 +1,25 @@
 <p align="center">
-  <img alt="LeRobot, Hugging Face Robotics Library" src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/lerobot-logo-thumbnail.png" width="100%">
+  <picture>
+    <source media="(prefers-color-scheme: dark)" srcset="media/lerobot-logo-thumbnail.png">
+    <source media="(prefers-color-scheme: light)" srcset="media/lerobot-logo-thumbnail.png">
+    <img alt="LeRobot, Hugging Face Robotics Library" src="media/lerobot-logo-thumbnail.png" style="max-width: 100%;">
+  </picture>
   <br/>
   <br/>
 </p>
 
 <div align="center">
 
-[![Tests](https://github.com/huggingface/lerobot/actions/workflows/nightly.yml/badge.svg?branch=main)](https://github.com/huggingface/lerobot/actions/workflows/nightly.yml?query=branch%3Amain)
+[![Tests](https://github.com/huggingface/lerobot/actions/workflows/nightly-tests.yml/badge.svg?branch=main)](https://github.com/huggingface/lerobot/actions/workflows/nightly-tests.yml?query=branch%3Amain)
+[![Coverage](https://codecov.io/gh/huggingface/lerobot/branch/main/graph/badge.svg?token=TODO)](https://codecov.io/gh/huggingface/lerobot)
 [![Python versions](https://img.shields.io/pypi/pyversions/lerobot)](https://www.python.org/downloads/)
 [![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://github.com/huggingface/lerobot/blob/main/LICENSE)
 [![Status](https://img.shields.io/pypi/status/lerobot)](https://pypi.org/project/lerobot/)
 [![Version](https://img.shields.io/pypi/v/lerobot)](https://pypi.org/project/lerobot/)
-[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-v2.1-ff69b4.svg)](https://github.com/huggingface/lerobot/blob/main/CODE_OF_CONDUCT.md)
+[![Examples](https://img.shields.io/badge/Examples-green.svg)](https://github.com/huggingface/lerobot/tree/main/examples)
+[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-v2.1%20adopted-ff69b4.svg)](https://github.com/huggingface/lerobot/blob/main/CODE_OF_CONDUCT.md)
 [![Discord](https://dcbadge.vercel.app/api/server/C5P34WJ68S?style=flat)](https://discord.gg/s3KuuzsPFb)
 
-<!-- [![Coverage](https://codecov.io/gh/huggingface/lerobot/branch/main/graph/badge.svg?token=TODO)](https://codecov.io/gh/huggingface/lerobot) -->
-
 </div>
 
 <h2 align="center">
@@ -25,10 +29,10 @@
 
 <div align="center">
   <img
-    src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/hope_jr/hopejr.png"
+    src="media/hope_jr/hopejr.png?raw=true"
     alt="HopeJR robot"
     title="HopeJR robot"
-    width="60%"
+    style="width: 60%;"
   />
 
   <p><strong>Meet HopeJR – A humanoid robot arm and hand for dexterous manipulation!</strong></p>
@@ -47,12 +51,20 @@
 </h2>
 
 <div align="center">
-  <table>
-    <tr>
-      <td align="center"><img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/so101/so101.webp" alt="SO-101 follower arm" title="SO-101 follower arm" width="90%"/></td>
-      <td align="center"><img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/so101/so101-leader.webp" alt="SO-101 leader arm" title="SO-101 leader arm" width="90%"/></td>
-    </tr>
-  </table>
+  <div style="display: flex; gap: 1rem; justify-content: center; align-items: center;" >
+    <img
+      src="media/so101/so101.webp?raw=true"
+      alt="SO-101 follower arm"
+      title="SO-101 follower arm"
+      style="width: 40%;"
+    />
+    <img
+      src="media/so101/so101-leader.webp?raw=true"
+      alt="SO-101 leader arm"
+      title="SO-101 leader arm"
+      style="width: 40%;"
+    />
+  </div>
 
   <p><strong>Meet the updated SO100, the SO-101 – Just €114 per arm!</strong></p>
   <p>Train it in minutes with a few simple moves on your laptop.</p>
@@ -64,7 +76,7 @@
   <p>Want to take it to the next level? Make your SO-101 mobile by building LeKiwi!</p>
   <p>Check out the <a href="https://huggingface.co/docs/lerobot/lekiwi">LeKiwi tutorial</a> and bring your robot to life on wheels.</p>
 
-  <img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/lekiwi/kiwi.webp" alt="LeKiwi mobile robot" title="LeKiwi mobile robot" width="50%">
+  <img src="media/lekiwi/kiwi.webp?raw=true" alt="LeKiwi mobile robot" title="LeKiwi mobile robot" width="50%">
 </div>
 
 <br/>
@@ -87,9 +99,9 @@
 
 <table>
   <tr>
-    <td><img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/gym/aloha_act.gif" width="100%" alt="ACT policy on ALOHA env"/></td>
-    <td><img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/gym/simxarm_tdmpc.gif" width="100%" alt="TDMPC policy on SimXArm env"/></td>
-    <td><img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/gym/pusht_diffusion.gif" width="100%" alt="Diffusion policy on PushT env"/></td>
+    <td><img src="media/gym/aloha_act.gif" width="100%" alt="ACT policy on ALOHA env"/></td>
+    <td><img src="media/gym/simxarm_tdmpc.gif" width="100%" alt="TDMPC policy on SimXArm env"/></td>
+    <td><img src="media/gym/pusht_diffusion.gif" width="100%" alt="Diffusion policy on PushT env"/></td>
   </tr>
   <tr>
     <td align="center">ACT policy on ALOHA env</td>
@@ -98,11 +110,23 @@
   </tr>
 </table>
 
+### Acknowledgment
+
+- The LeRobot team 🤗 for building SmolVLA [Paper](https://arxiv.org/abs/2506.01844), [Blog](https://huggingface.co/blog/smolvla).
+- Thanks to Tony Zhao, Zipeng Fu and colleagues for open sourcing ACT policy, ALOHA environments and datasets. Ours are adapted from [ALOHA](https://tonyzhaozh.github.io/aloha) and [Mobile ALOHA](https://mobile-aloha.github.io).
+- Thanks to Cheng Chi, Zhenjia Xu and colleagues for open sourcing Diffusion policy, Pusht environment and datasets, as well as UMI datasets. Ours are adapted from [Diffusion Policy](https://diffusion-policy.cs.columbia.edu) and [UMI Gripper](https://umi-gripper.github.io).
+- Thanks to Nicklas Hansen, Yunhai Feng and colleagues for open sourcing TDMPC policy, Simxarm environments and datasets. Ours are adapted from [TDMPC](https://github.com/nicklashansen/tdmpc) and [FOWM](https://www.yunhaifeng.com/FOWM).
+- Thanks to Antonio Loquercio and Ashish Kumar for their early support.
+- Thanks to [Seungjae (Jay) Lee](https://sjlee.cc/), [Mahi Shafiullah](https://mahis.life/) and colleagues for open sourcing [VQ-BeT](https://sjlee.cc/vq-bet/) policy and helping us adapt the codebase to our repository. The policy is adapted from [VQ-BeT repo](https://github.com/jayLEE0301/vq_bet_official).
+
 ## Installation
 
-LeRobot works with Python 3.10+ and PyTorch 2.2+.
+Download our source code:
 
-### Environment Setup
+```bash
+git clone https://github.com/huggingface/lerobot.git
+cd lerobot
+```
 
 Create a virtual environment with Python 3.10 and activate it, e.g. with [`miniconda`](https://docs.anaconda.com/free/miniconda/index.html):
 
@@ -127,18 +151,7 @@ conda install ffmpeg -c conda-forge
 >
 > - _[On Linux only]_ Install [ffmpeg build dependencies](https://trac.ffmpeg.org/wiki/CompilationGuide/Ubuntu#GettheDependencies) and [compile ffmpeg from source with libsvtav1](https://trac.ffmpeg.org/wiki/CompilationGuide/Ubuntu#libsvtav1), and make sure you use the corresponding ffmpeg binary to your install with `which ffmpeg`.
 
-### Install LeRobot 🤗
-
-#### From Source
-
-First, clone the repository and navigate into the directory:
-
-```bash
-git clone https://github.com/huggingface/lerobot.git
-cd lerobot
-```
-
-Then, install the library in editable mode. This is useful if you plan to contribute to the code.
+Install 🤗 LeRobot:
 
 ```bash
 pip install -e .
@@ -159,34 +172,6 @@ For instance, to install 🤗 LeRobot with aloha and pusht, use:
 pip install -e ".[aloha, pusht]"
 ```
 
-### Installation from PyPI
-
-**Core Library:**
-Install the base package with:
-
-```bash
-pip install lerobot
-```
-
-_This installs only the default dependencies._
-
-**Extra Features:**
-To install additional functionality, use one of the following:
-
-```bash
-pip install 'lerobot[all]'          # All available features
-pip install 'lerobot[aloha,pusht]'  # Specific features (Aloha & Pusht)
-pip install 'lerobot[feetech]'      # Feetech motor support
-```
-
-_Replace `[...]` with your desired features._
-
-**Available Tags:**
-For a full list of optional dependencies, see:
-https://pypi.org/project/lerobot/
-
-### Weights & Biases
-
 To use [Weights and Biases](https://docs.wandb.ai/quickstart) for experiment tracking, log in with
 
 ```bash
@@ -197,7 +182,7 @@ wandb login
 
 ### Visualize datasets
 
-Check out [example 1](https://github.com/huggingface/lerobot/blob/main/examples/1_load_lerobot_dataset.py) that illustrates how to use our dataset class which automatically downloads data from the Hugging Face hub.
+Check out [example 1](./examples/1_load_lerobot_dataset.py) that illustrates how to use our dataset class which automatically downloads data from the Hugging Face hub.
 
 You can also locally visualize episodes from a dataset on the hub by executing our script from the command line:
 
@@ -227,7 +212,7 @@ Our script can also visualize datasets stored on a distant server. See `python -
 
 A dataset in `LeRobotDataset` format is very simple to use. It can be loaded from a repository on the Hugging Face hub or a local folder simply with e.g. `dataset = LeRobotDataset("lerobot/aloha_static_coffee")` and can be indexed into like any Hugging Face and PyTorch dataset. For instance `dataset[0]` will retrieve a single temporal frame from the dataset containing observation(s) and an action as PyTorch tensors ready to be fed to a model.
 
-A specificity of `LeRobotDataset` is that, rather than retrieving a single frame by its index, we can retrieve several frames based on their temporal relationship with the indexed frame, by setting `delta_timestamps` to a list of relative times with respect to the indexed frame. For example, with `delta_timestamps = {"observation.image": [-1, -0.5, -0.2, 0]}` one can retrieve, for a given index, 4 frames: 3 "previous" frames 1 second, 0.5 seconds, and 0.2 seconds before the indexed frame, and the indexed frame itself (corresponding to the 0 entry). See example [1_load_lerobot_dataset.py](https://github.com/huggingface/lerobot/blob/main/examples/1_load_lerobot_dataset.py) for more details on `delta_timestamps`.
+A specificity of `LeRobotDataset` is that, rather than retrieving a single frame by its index, we can retrieve several frames based on their temporal relationship with the indexed frame, by setting `delta_timestamps` to a list of relative times with respect to the indexed frame. For example, with `delta_timestamps = {"observation.image": [-1, -0.5, -0.2, 0]}` one can retrieve, for a given index, 4 frames: 3 "previous" frames 1 second, 0.5 seconds, and 0.2 seconds before the indexed frame, and the indexed frame itself (corresponding to the 0 entry). See example [1_load_lerobot_dataset.py](examples/1_load_lerobot_dataset.py) for more details on `delta_timestamps`.
 
 Under the hood, the `LeRobotDataset` format makes use of several ways to serialize data which can be useful to understand if you plan to work more closely with this format. We tried to make a flexible yet simple dataset format that would cover most type of features and specificities present in reinforcement learning and robotics, in simulation and in real-world, with a focus on cameras and robot states but easily extended to other types of sensory inputs as long as they can be represented by a tensor.
 
@@ -271,12 +256,12 @@ Dataset can be uploaded/downloaded from the HuggingFace hub seamlessly. To work
 
 ### Evaluate a pretrained policy
 
-Check out [example 2](https://github.com/huggingface/lerobot/blob/main/examples/2_evaluate_pretrained_policy.py) that illustrates how to download a pretrained policy from Hugging Face hub, and run an evaluation on its corresponding environment.
+Check out [example 2](./examples/2_evaluate_pretrained_policy.py) that illustrates how to download a pretrained policy from Hugging Face hub, and run an evaluation on its corresponding environment.
 
 We also provide a more capable script to parallelize the evaluation over multiple environments during the same rollout. Here is an example with a pretrained model hosted on [lerobot/diffusion_pusht](https://huggingface.co/lerobot/diffusion_pusht):
 
 ```bash
-lerobot-eval \
+python -m lerobot.scripts.eval \
     --policy.path=lerobot/diffusion_pusht \
     --env.type=pusht \
     --eval.batch_size=10 \
@@ -288,22 +273,22 @@ lerobot-eval \
 Note: After training your own policy, you can re-evaluate the checkpoints with:
 
 ```bash
-lerobot-eval --policy.path={OUTPUT_DIR}/checkpoints/last/pretrained_model
+python -m lerobot.scripts.eval --policy.path={OUTPUT_DIR}/checkpoints/last/pretrained_model
 ```
 
-See `lerobot-eval --help` for more instructions.
+See `python -m lerobot.scripts.eval --help` for more instructions.
 
 ### Train your own policy
 
-Check out [example 3](https://github.com/huggingface/lerobot/blob/main/examples/3_train_policy.py) that illustrates how to train a model using our core library in python, and [example 4](https://github.com/huggingface/lerobot/blob/main/examples/4_train_policy_with_script.md) that shows how to use our training script from command line.
+Check out [example 3](./examples/3_train_policy.py) that illustrates how to train a model using our core library in python, and [example 4](./examples/4_train_policy_with_script.md) that shows how to use our training script from command line.
 
 To use wandb for logging training and evaluation curves, make sure you've run `wandb login` as a one-time setup step. Then, when running the training command above, enable WandB in the configuration by adding `--wandb.enable=true`.
 
-A link to the wandb logs for the run will also show up in yellow in your terminal. Here is an example of what they look like in your browser. Please also check [here](https://github.com/huggingface/lerobot/blob/main/examples/4_train_policy_with_script.md#typical-logs-and-metrics) for the explanation of some commonly used metrics in logs.
+A link to the wandb logs for the run will also show up in yellow in your terminal. Here is an example of what they look like in your browser. Please also check [here](./examples/4_train_policy_with_script.md#typical-logs-and-metrics) for the explanation of some commonly used metrics in logs.
 
-\<img src="https://raw.githubusercontent.com/huggingface/lerobot/main/media/wandb.png" alt="WandB logs example"\>
+![](media/wandb.png)
 
-Note: For efficiency, during training every checkpoint is evaluated on a low number of episodes. You may use `--eval.n_episodes=500` to evaluate on more episodes than the default. Or, after training, you may want to re-evaluate your best checkpoints on more episodes or change the evaluation settings. See `lerobot-eval --help` for more instructions.
+Note: For efficiency, during training every checkpoint is evaluated on a low number of episodes. You may use `--eval.n_episodes=500` to evaluate on more episodes than the default. Or, after training, you may want to re-evaluate your best checkpoints on more episodes or change the evaluation settings. See `python -m lerobot.scripts.eval --help` for more instructions.
 
 #### Reproduce state-of-the-art (SOTA)
 
@@ -311,7 +296,7 @@ We provide some pretrained policies on our [hub page](https://huggingface.co/ler
 You can reproduce their training by loading the config from their run. Simply running:
 
 ```bash
-lerobot-train --config_path=lerobot/diffusion_pusht
+python -m lerobot.scripts.train --config_path=lerobot/diffusion_pusht
 ```
 
 reproduces SOTA results for Diffusion Policy on the PushT task.
@@ -320,6 +305,26 @@ reproduces SOTA results for Diffusion Policy on the PushT task.
 
 If you would like to contribute to 🤗 LeRobot, please check out our [contribution guide](https://github.com/huggingface/lerobot/blob/main/CONTRIBUTING.md).
 
+<!-- ### Add a new dataset
+
+To add a dataset to the hub, you need to login using a write-access token, which can be generated from the [Hugging Face settings](https://huggingface.co/settings/tokens):
+```bash
+huggingface-cli login --token ${HUGGINGFACE_TOKEN} --add-to-git-credential
+```
+
+Then point to your raw dataset folder (e.g. `data/aloha_static_pingpong_test_raw`), and push your dataset to the hub with:
+```bash
+python lerobot/scripts/push_dataset_to_hub.py \
+--raw-dir data/aloha_static_pingpong_test_raw \
+--out-dir data \
+--repo-id lerobot/aloha_static_pingpong_test \
+--raw-format aloha_hdf5
+```
+
+See `python lerobot/scripts/push_dataset_to_hub.py --help` for more instructions.
+
+If your dataset format is not supported, implement your own in `lerobot/datasets/push_dataset_to_hub/${raw_format}_format.py` by copying examples like [pusht_zarr](https://github.com/huggingface/lerobot/blob/main/lerobot/datasets/push_dataset_to_hub/pusht_zarr_format.py), [umi_zarr](https://github.com/huggingface/lerobot/blob/main/lerobot/datasets/push_dataset_to_hub/umi_zarr_format.py), [aloha_hdf5](https://github.com/huggingface/lerobot/blob/main/lerobot/datasets/push_dataset_to_hub/aloha_hdf5_format.py), or [xarm_pkl](https://github.com/huggingface/lerobot/blob/main/lerobot/datasets/push_dataset_to_hub/xarm_pkl_format.py). -->
+
 ### Add a pretrained policy
 
 Once you have trained a policy you may upload it to the Hugging Face hub using a hub id that looks like `${hf_user}/${repo_name}` (e.g. [lerobot/diffusion_pusht](https://huggingface.co/lerobot/diffusion_pusht)).
@@ -336,16 +341,34 @@ To upload these to the hub, run the following:
 huggingface-cli upload ${hf_user}/${repo_name} path/to/pretrained_model
 ```
 
-See [eval.py](https://github.com/huggingface/lerobot/blob/main/src/lerobot/scripts/eval.py) for an example of how other people may use your policy.
+See [eval.py](https://github.com/huggingface/lerobot/blob/main/lerobot/scripts/eval.py) for an example of how other people may use your policy.
 
-### Acknowledgment
+### Improve your code with profiling
 
-- The LeRobot team 🤗 for building SmolVLA [Paper](https://arxiv.org/abs/2506.01844), [Blog](https://huggingface.co/blog/smolvla).
-- Thanks to Tony Zhao, Zipeng Fu and colleagues for open sourcing ACT policy, ALOHA environments and datasets. Ours are adapted from [ALOHA](https://tonyzhaozh.github.io/aloha) and [Mobile ALOHA](https://mobile-aloha.github.io).
-- Thanks to Cheng Chi, Zhenjia Xu and colleagues for open sourcing Diffusion policy, Pusht environment and datasets, as well as UMI datasets. Ours are adapted from [Diffusion Policy](https://diffusion-policy.cs.columbia.edu) and [UMI Gripper](https://umi-gripper.github.io).
-- Thanks to Nicklas Hansen, Yunhai Feng and colleagues for open sourcing TDMPC policy, Simxarm environments and datasets. Ours are adapted from [TDMPC](https://github.com/nicklashansen/tdmpc) and [FOWM](https://www.yunhaifeng.com/FOWM).
-- Thanks to Antonio Loquercio and Ashish Kumar for their early support.
-- Thanks to [Seungjae (Jay) Lee](https://sjlee.cc/), [Mahi Shafiullah](https://mahis.life/) and colleagues for open sourcing [VQ-BeT](https://sjlee.cc/vq-bet/) policy and helping us adapt the codebase to our repository. The policy is adapted from [VQ-BeT repo](https://github.com/jayLEE0301/vq_bet_official).
+An example of a code snippet to profile the evaluation of a policy:
+
+<!-- prettier-ignore-start -->
+```python
+from torch.profiler import profile, record_function, ProfilerActivity
+
+def trace_handler(prof):
+    prof.export_chrome_trace(f"tmp/trace_schedule_{prof.step_num}.json")
+
+with profile(
+    activities=[ProfilerActivity.CPU, ProfilerActivity.CUDA],
+    schedule=torch.profiler.schedule(
+        wait=2,
+        warmup=2,
+        active=3,
+    ),
+    on_trace_ready=trace_handler
+) as prof:
+    with record_function("eval_policy"):
+        for i in range(num_episodes):
+            prof.step()
+            # insert code to profile, potentially whole body of eval_policy function
+```
+<!-- prettier-ignore-end -->
 
 ## Citation
 
@@ -353,13 +376,83 @@ If you want, you can cite this work with:
 
 ```bibtex
 @misc{cadene2024lerobot,
-    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
+    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascale, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
     title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
     howpublished = "\url{https://github.com/huggingface/lerobot}",
     year = {2024}
 }
 ```
 
+Additionally, if you are using any of the particular policy architecture, pretrained models, or datasets, it is recommended to cite the original authors of the work as they appear below:
+
+- [SmolVLA](https://arxiv.org/abs/2506.01844)
+
+```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}
+}
+```
+
+- [Diffusion Policy](https://diffusion-policy.cs.columbia.edu)
+
+```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},
+}
+```
+
+- [ACT or ALOHA](https://tonyzhaozh.github.io/aloha)
+
+```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}
+}
+```
+
+- [TDMPC](https://www.nicklashansen.com/td-mpc/)
+
+```bibtex
+@inproceedings{Hansen2022tdmpc,
+	title={Temporal Difference Learning for Model Predictive Control},
+	author={Nicklas Hansen and Xiaolong Wang and Hao Su},
+	booktitle={ICML},
+	year={2022}
+}
+```
+
+- [VQ-BeT](https://sjlee.cc/vq-bet/)
+
+```bibtex
+@article{lee2024behavior,
+  title={Behavior generation with latent actions},
+  author={Lee, Seungjae and Wang, Yibin and Etukuru, Haritheja and Kim, H Jin and Shafiullah, Nur Muhammad Mahi and Pinto, Lerrel},
+  journal={arXiv preprint arXiv:2403.03181},
+  year={2024}
+}
+```
+
+- [HIL-SERL](https://hil-serl.github.io/)
+
+```bibtex
+@Article{luo2024hilserl,
+title={Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning},
+author={Jianlan Luo and Charles Xu and Jeffrey Wu and Sergey Levine},
+year={2024},
+eprint={2410.21845},
+archivePrefix={arXiv},
+primaryClass={cs.RO}
+}
+```
+
 ## Star History
 
 [![Star History Chart](https://api.star-history.com/svg?repos=huggingface/lerobot&type=Timeline)](https://star-history.com/#huggingface/lerobot&Timeline)

accelerate_configs/1gpu_config.yaml

@@ -1,11 +0,0 @@
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: NO
-downcast_bf16: 'no'
-enable_cpu_affinity: false
-machine_rank: 0
-main_training_function: main
-mixed_precision: 'no'
-num_machines: 1
-num_processes: 1
-use_cpu: false

accelerate_configs/2gpu_config_safe.yaml

@@ -1,18 +0,0 @@
-compute_environment: LOCAL_MACHINE
-debug: false
-distributed_type: MULTI_GPU
-downcast_bf16: 'no'
-enable_cpu_affinity: false
-gpu_ids: all
-machine_rank: 0
-main_training_function: main
-mixed_precision: 'no'
-num_machines: 1
-num_processes: 2
-rdzv_backend: static
-same_network: true
-tpu_env: []
-tpu_use_cluster: false
-tpu_use_sudo: false
-use_cpu: false
-dynamo_backend: "no"

docker/Dockerfile.user

@@ -29,7 +29,7 @@ ENV DEBIAN_FRONTEND=noninteractive \
 
 # Install system dependencies and uv (as root)
 RUN apt-get update && apt-get install -y --no-install-recommends \
-    build-essential git curl libglib2.0-0 libegl1-mesa-dev ffmpeg \
+    build-essential git curl libglib2.0-0 libegl1-mesa ffmpeg \
     libusb-1.0-0-dev speech-dispatcher libgeos-dev portaudio19-dev \
     && curl -LsSf https://astral.sh/uv/install.sh | sh \
     && mv /root/.local/bin/uv /usr/local/bin/uv \

docs-requirements.txt

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

docs/README.md

@@ -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 . -r docs-requirements.txt
+pip install -e ".[docs]"
 ```
 
 You will also need `nodejs`. Please refer to their [installation page](https://nodejs.org/en/download)

docs/source/_toctree.yml

@@ -13,6 +13,8 @@
     title: Cameras
   - local: integrate_hardware
     title: Bring Your Own Hardware
+  - local: processor_tutorial
+    title: RobotProcessor Pipeline
   - local: hilserl
     title: Train a Robot with RL
   - local: hilserl_sim
@@ -39,8 +41,6 @@
 - sections:
   - local: notebooks
     title: Notebooks
-  - local: feetech
-    title: Updating Feetech Firmware
   title: "Resources"
 - sections:
   - local: contributing

docs/source/cameras.mdx

@@ -9,7 +9,7 @@ To instantiate a camera, you need a camera identifier. This identifier might cha
 To find the camera indices of the cameras plugged into your system, run the following script:
 
 ```bash
-lerobot-find-cameras opencv # or realsense for Intel Realsense cameras
+python -m lerobot.find_cameras opencv # or realsense for Intel Realsense cameras
 ```
 
 The output will look something like this if you have two cameras connected:

docs/source/feetech.mdx

@@ -1,71 +0,0 @@
-# Feetech Motor Firmware Update
-
-This tutorial guides you through updating the firmware of Feetech motors using the official Feetech software.
-
-## Prerequisites
-
-- Windows computer (Feetech software is only available for Windows)
-- Feetech motor control board
-- USB cable to connect the control board to your computer
-- Feetech motors connected to the control board
-
-## Step 1: Download Feetech Software
-
-1. Visit the official Feetech software download page: [https://www.feetechrc.com/software.html](https://www.feetechrc.com/software.html)
-2. Download the latest version of the Feetech debugging software (FD)
-3. Install the software on your Windows computer
-
-## Step 2: Hardware Setup
-
-1. Connect your Feetech motors to the motor control board
-2. Connect the motor control board to your Windows computer via USB cable
-3. Ensure power is supplied to the motors
-
-## Step 3: Configure Connection
-
-1. Launch the Feetech debugging software
-2. Select the correct COM port from the port dropdown menu
-   - If unsure which port to use, check Windows Device Manager under "Ports (COM & LPT)"
-3. Set the appropriate baud rate (typically 1000000 for most Feetech motors)
-4. Click "Open" to establish communication with the control board
-
-## Step 4: Scan for Motors
-
-1. Once connected, click the "Search" button to detect all connected motors
-2. The software will automatically discover and list all motors on the bus
-3. Each motor will appear with its ID number
-
-## Step 5: Update Firmware
-
-For each motor you want to update:
-
-1. **Select the motor** from the list by clicking on it
-2. **Click on Upgrade tab**:
-3. **Click on Online button**:
-   - If an potential firmware update is found, it will be displayed in the box
-4. **Click on Upgrade button**:
-   - The update progress will be displayed
-
-## Step 6: Verify Update
-
-1. After the update completes, the software should automatically refresh the motor information
-2. Verify that the firmware version has been updated to the expected version
-
-## Important Notes
-
-⚠️ **Warning**: Do not disconnect power or USB during firmware updates, it will potentially brick the motor.
-
-## Bonus: Motor Debugging on Linux/macOS
-
-For debugging purposes only, you can use the open-source Feetech Debug Tool:
-
-- **Repository**: [FT_SCServo_Debug_Qt](https://github.com/CarolinePascal/FT_SCServo_Debug_Qt/tree/fix/port-search-timer)
-
-### Installation Instructions
-
-Follow the instructions in the repository to install the tool, for Ubuntu you can directly install it, for MacOS you need to build it from source.
-
-**Limitations:**
-
-- This tool is for debugging and parameter adjustment only
-- Firmware updates must still be done on Windows with official Feetech software

docs/source/hilserl.mdx

@@ -56,27 +56,41 @@ pip install -e ".[hilserl]"
 
 ### Understanding Configuration
 
-The training process begins with proper configuration for the HILSerl environment. The configuration class of interest is `HILSerlRobotEnvConfig` in `lerobot/envs/configs.py`. Which is defined as:
+The training process begins with proper configuration for the HILSerl environment. The main configuration class is `GymManipulatorConfig` in `lerobot/scripts/rl/gym_manipulator.py`, which contains nested `HILSerlRobotEnvConfig` and `DatasetConfig`. The configuration is organized into focused, nested sub-configs:
 
 <!-- prettier-ignore-start -->
 ```python
+class GymManipulatorConfig:
+    env: HILSerlRobotEnvConfig    # Environment configuration (nested)
+    dataset: DatasetConfig    # Dataset recording/replay configuration (nested)
+    mode: str | None = None    # "record", "replay", or None (for training)
+
 class HILSerlRobotEnvConfig(EnvConfig):
     robot: RobotConfig | None = None    # Main robot agent (defined in `lerobot/robots`)
-    teleop: TeleoperatorConfig | None = None    # Teleoperator agent, e.g., gamepad or leader arm, (defined in `lerobot/teleoperators`)
-    wrapper: EnvTransformConfig | None = None    # Environment wrapper settings; check `lerobot/scripts/server/gym_manipulator.py`
-    fps: int = 10    # Control frequency
+    teleop: TeleoperatorConfig | None = None    # Teleoperator agent, e.g., gamepad or leader arm
+    processor: HILSerlProcessorConfig    # Processing pipeline configuration (nested)
     name: str = "real_robot"    # Environment name
-    mode: str = None    # "record", "replay", or None (for training)
-    repo_id: str | None = None    # LeRobot dataset repository ID
-    dataset_root: str | None = None    # Local dataset root (optional)
-    task: str = ""    # Task identifier
-    num_episodes: int = 10    # Number of episodes for recording
-    episode: int = 0    # episode index for replay
     device: str = "cuda"    # Compute device
-    push_to_hub: bool = True    # Whether to push the recorded datasets to Hub
-    pretrained_policy_name_or_path: str | None = None    # For policy loading
-    reward_classifier_pretrained_path: str | None = None    # For reward model
-    number_of_steps_after_success: int = 0    # For reward classifier, collect more positive examples after a success to train a classifier
+    fps: int = 30    # Control frequency
+
+# Nested processor configuration
+class HILSerlProcessorConfig:
+    control_mode: str = "gamepad"    # Control mode
+    observation: ObservationConfig    # Observation processing settings
+    image_preprocessing: ImagePreprocessingConfig    # Image crop/resize settings
+    gripper: GripperConfig    # Gripper control and penalty settings
+    reset: ResetConfig    # Environment reset and timing settings
+    inverse_kinematics: InverseKinematicsConfig    # IK processing settings
+    reward_classifier: RewardClassifierConfig    # Reward classifier settings
+
+# Dataset configuration
+class DatasetConfig:
+    repo_id: str    # LeRobot dataset repository ID
+    dataset_root: str | None = None    # Local dataset root (optional)
+    task: str    # Task identifier
+    num_episodes: int    # Number of episodes for recording
+    episode: int    # Episode index for replay
+    push_to_hub: bool    # Whether to push datasets to Hub
 ```
 <!-- prettier-ignore-end -->
 
@@ -130,22 +144,31 @@ With the bounds defined, you can safely collect demonstrations for training. Tra
 
 Create a configuration file for recording demonstrations (or edit an existing one like [env_config_so100.json](https://huggingface.co/datasets/aractingi/lerobot-example-config-files/blob/main/env_config_so100.json)):
 
-1. Set `mode` to `"record"`
-2. Specify a unique `repo_id` for your dataset (e.g., "username/task_name")
-3. Set `num_episodes` to the number of demonstrations you want to collect
-4. Set `crop_params_dict` to `null` initially (we'll determine crops later)
-5. Configure `robot`, `cameras`, and other hardware settings
+1. Set `mode` to `"record"` at the root level
+2. Specify a unique `repo_id` for your dataset in the `dataset` section (e.g., "username/task_name")
+3. Set `num_episodes` in the `dataset` section to the number of demonstrations you want to collect
+4. Set `env.processor.image_preprocessing.crop_params_dict` to `{}` initially (we'll determine crops later)
+5. Configure `env.robot`, `env.teleop`, and other hardware settings in the `env` section
 
 Example configuration section:
 
 ```json
-"mode": "record",
-"repo_id": "username/pick_lift_cube",
-"dataset_root": null,
-"task": "pick_and_lift",
-"num_episodes": 15,
-"episode": 0,
-"push_to_hub": true
+{
+  "env": {
+    "type": "gym_manipulator",
+    "fps": 10
+    // ... robot, teleop, processor configs ...
+  },
+  "dataset": {
+    "repo_id": "username/pick_lift_cube",
+    "dataset_root": null,
+    "task": "pick_and_lift",
+    "num_episodes": 15,
+    "episode": 0,
+    "push_to_hub": true
+  },
+  "mode": "record"
+}
 ```
 
 ### Using a Teleoperation Device
@@ -191,10 +214,17 @@ The gamepad provides a very convenient way to control the robot and the episode
 To setup the gamepad, you need to set the `control_mode` to `"gamepad"` and define the `teleop` section in the configuration file.
 
 ```json
+{
+  "env": {
     "teleop": {
-        "type": "gamepad",
-        "use_gripper": true
+      "type": "gamepad",
+      "use_gripper": true
     },
+    "processor": {
+      "control_mode": "gamepad"
+    }
+  }
+}
 ```
 
 <p align="center">
@@ -216,11 +246,18 @@ The SO101 leader arm has reduced gears that allows it to move and track the foll
 To setup the SO101 leader, you need to set the `control_mode` to `"leader"` and define the `teleop` section in the configuration file.
 
 ```json
+{
+  "env": {
     "teleop": {
-        "type": "so101_leader",
-        "port": "/dev/tty.usbmodem585A0077921", # check your port number
-        "use_degrees": true
+      "type": "so101_leader",
+      "port": "/dev/tty.usbmodem585A0077921",
+      "use_degrees": true
     },
+    "processor": {
+      "control_mode": "leader"
+    }
+  }
+}
 ```
 
 In order to annotate the success/failure of the episode, **you will need** to use a keyboard to press `s` for success, `esc` for failure.
@@ -251,7 +288,7 @@ python -m lerobot.scripts.rl.gym_manipulator --config_path src/lerobot/configs/e
 
 During recording:
 
-1. The robot will reset to the initial position defined in the configuration file `fixed_reset_joint_positions`
+1. The robot will reset to the initial position defined in the configuration file `env.processor.reset.fixed_reset_joint_positions`
 2. Complete the task successfully
 3. The episode ends with a reward of 1 when you press the "success" button
 4. If the time limit is reached, or the fail button is pressed, the episode ends with a reward of 0
@@ -310,11 +347,19 @@ observation.images.front: [180, 250, 120, 150]
 Add these crop parameters to your training configuration:
 
 ```json
-"crop_params_dict": {
-    "observation.images.side": [180, 207, 180, 200],
-    "observation.images.front": [180, 250, 120, 150]
-},
-"resize_size": [128, 128]
+{
+  "env": {
+    "processor": {
+      "image_preprocessing": {
+        "crop_params_dict": {
+          "observation.images.side": [180, 207, 180, 200],
+          "observation.images.front": [180, 250, 120, 150]
+        },
+        "resize_size": [128, 128]
+      }
+    }
+  }
+}
 ```
 
 **Recommended image resolution**
@@ -343,26 +388,35 @@ python -m lerobot.scripts.rl.gym_manipulator --config_path src/lerobot/configs/r
 
 **Key Parameters for Data Collection**
 
-- **mode**: set it to `"record"` to collect a dataset
-- **repo_id**: `"hf_username/dataset_name"`, name of the dataset and repo on the hub
-- **num_episodes**: Number of episodes to record
-- **number_of_steps_after_success**: Number of additional frames to record after a success (reward=1) is detected
-- **fps**: Number of frames per second to record
-- **push_to_hub**: Whether to push the dataset to the hub
+- **mode**: set it to `"record"` to collect a dataset (at root level)
+- **dataset.repo_id**: `"hf_username/dataset_name"`, name of the dataset and repo on the hub
+- **dataset.num_episodes**: Number of episodes to record
+- **env.processor.reset.number_of_steps_after_success**: Number of additional frames to record after a success (reward=1) is detected
+- **env.fps**: Number of frames per second to record
+- **dataset.push_to_hub**: Whether to push the dataset to the hub
 
-The `number_of_steps_after_success` parameter is crucial as it allows you to collect more positive examples. When a success is detected, the system will continue recording for the specified number of steps while maintaining the reward=1 label. Otherwise, there won't be enough states in the dataset labeled to 1 to train a good classifier.
+The `env.processor.reset.number_of_steps_after_success` parameter is crucial as it allows you to collect more positive examples. When a success is detected, the system will continue recording for the specified number of steps while maintaining the reward=1 label. Otherwise, there won't be enough states in the dataset labeled to 1 to train a good classifier.
 
 Example configuration section for data collection:
 
 ```json
 {
-  "mode": "record",
-  "repo_id": "hf_username/dataset_name",
-  "dataset_root": "data/your_dataset",
-  "num_episodes": 20,
-  "push_to_hub": true,
-  "fps": 10,
-  "number_of_steps_after_success": 15
+  "env": {
+    "type": "gym_manipulator",
+    "fps": 10,
+    "processor": {
+      "reset": {
+        "number_of_steps_after_success": 15
+      }
+    }
+  },
+  "dataset": {
+    "repo_id": "hf_username/dataset_name",
+    "dataset_root": "data/your_dataset",
+    "num_episodes": 20,
+    "push_to_hub": true
+  },
+  "mode": "record"
 }
 ```
 
@@ -412,7 +466,7 @@ Example configuration for training the [reward classifier](https://huggingface.c
 To train the classifier, use the `train.py` script with your configuration:
 
 ```bash
-lerobot-train --config_path path/to/reward_classifier_train_config.json
+python -m lerobot.scripts.train --config_path path/to/reward_classifier_train_config.json
 ```
 
 **Deploying and Testing the Model**
@@ -421,9 +475,17 @@ To use your trained reward classifier, configure the `HILSerlRobotEnvConfig` to
 
 <!-- prettier-ignore-start -->
 ```python
-env_config = HILSerlRobotEnvConfig(
-    reward_classifier_pretrained_path="path_to_your_pretrained_trained_model",
-    # Other environment parameters
+config = GymManipulatorConfig(
+    env=HILSerlRobotEnvConfig(
+        processor=HILSerlProcessorConfig(
+            reward_classifier=RewardClassifierConfig(
+                pretrained_path="path_to_your_pretrained_trained_model"
+            )
+        ),
+        # Other environment parameters
+    ),
+    dataset=DatasetConfig(...),
+    mode=None  # For training
 )
 ```
 <!-- prettier-ignore-end -->
@@ -432,7 +494,15 @@ or set the argument in the json config file.
 
 ```json
 {
-  "reward_classifier_pretrained_path": "path_to_your_pretrained_model"
+  "env": {
+    "processor": {
+      "reward_classifier": {
+        "pretrained_path": "path_to_your_pretrained_model",
+        "success_threshold": 0.7,
+        "success_reward": 1.0
+      }
+    }
+  }
 }
 ```
 
@@ -458,7 +528,7 @@ The reward classifier will automatically provide rewards based on the visual inp
 3. **Train the classifier**:
 
    ```bash
-   lerobot-train --config_path src/lerobot/configs/reward_classifier_train_config.json
+   python -m lerobot.scripts.train --config_path src/lerobot/configs/reward_classifier_train_config.json
    ```
 
 4. **Test the classifier**:

docs/source/hope_jr.mdx

@@ -19,7 +19,7 @@ pip install -e ".[hopejr]"
 Before starting calibration and operation, you need to identify the USB ports for each HopeJR component. Run this script to find the USB ports for the arm, hand, glove, and exoskeleton:
 
 ```bash
-lerobot-find-port
+python -m lerobot.find_port
 ```
 
 This will display the available USB ports and their associated devices. Make note of the port paths (e.g., `/dev/tty.usbmodem58760433331`, `/dev/tty.usbmodem11301`) as you'll need to specify them in the `--robot.port` and `--teleop.port` parameters when recording data, replaying episodes, or running teleoperation scripts.
@@ -31,7 +31,7 @@ Before performing teleoperation, HopeJR's limbs need to be calibrated. Calibrati
 ### 1.1 Calibrate Robot Hand
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=hope_jr_hand \
     --robot.port=/dev/tty.usbmodem58760432281 \
     --robot.id=blue \
@@ -81,7 +81,7 @@ Once you have set the appropriate boundaries for all joints, click "Save" to sav
 ### 1.2 Calibrate Teleoperator Glove
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=homunculus_glove \
     --teleop.port=/dev/tty.usbmodem11201 \
     --teleop.id=red \
@@ -120,7 +120,7 @@ Once calibration is complete, the system will save the calibration to `/Users/yo
 ### 1.3 Calibrate Robot Arm
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=hope_jr_arm \
     --robot.port=/dev/tty.usbserial-1110 \
     --robot.id=white
@@ -146,7 +146,7 @@ Use the calibration interface to set the range boundaries for each joint. Move e
 ### 1.4 Calibrate Teleoperator Exoskeleton
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=homunculus_arm \
     --teleop.port=/dev/tty.usbmodem11201 \
     --teleop.id=black
@@ -178,7 +178,7 @@ Due to global variable conflicts in the Feetech middleware, teleoperation for ar
 ### Hand
 
 ```bash
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
     --robot.type=hope_jr_hand \
     --robot.port=/dev/tty.usbmodem58760432281 \
     --robot.id=blue \
@@ -194,7 +194,7 @@ lerobot-teleoperate \
 ### Arm
 
 ```bash
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
     --robot.type=hope_jr_arm \
     --robot.port=/dev/tty.usbserial-1110 \
     --robot.id=white \
@@ -214,7 +214,7 @@ Record, Replay and Train with Hope-JR is still experimental.
 This step records the dataset, which can be seen as an example [here](https://huggingface.co/datasets/nepyope/hand_record_test_with_video_data/settings).
 
 ```bash
-lerobot-record \
+python -m lerobot.record \
     --robot.type=hope_jr_hand \
     --robot.port=/dev/tty.usbmodem58760432281 \
     --robot.id=right \
@@ -236,7 +236,7 @@ lerobot-record \
 ### Replay
 
 ```bash
-lerobot-replay \
+python -m lerobot.replay \
     --robot.type=hope_jr_hand \
     --robot.port=/dev/tty.usbmodem58760432281 \
     --robot.id=right \
@@ -248,7 +248,7 @@ lerobot-replay \
 ### Train
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --dataset.repo_id=nepyope/hand_record_test_with_video_data \
   --policy.type=act \
   --output_dir=outputs/train/hopejr_hand \
@@ -263,7 +263,7 @@ lerobot-train \
 This training run can be viewed as an example [here](https://wandb.ai/tino/lerobot/runs/rp0k8zvw?nw=nwusertino).
 
 ```bash
-lerobot-record \
+python -m lerobot.record \
   --robot.type=hope_jr_hand \
   --robot.port=/dev/tty.usbmodem58760432281 \
   --robot.id=right \

docs/source/il_robots.mdx

@@ -45,7 +45,7 @@ Note that the `id` associated with a robot is used to store the calibration file
 <hfoptions id="teleoperate_so101">
 <hfoption id="Command">
 ```bash
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.id=my_awesome_follower_arm \
@@ -101,7 +101,7 @@ With `rerun`, you can teleoperate again while simultaneously visualizing the cam
 <hfoptions id="teleoperate_koch_camera">
 <hfoption id="Command">
 ```bash
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
     --robot.type=koch_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.id=my_awesome_follower_arm \
@@ -174,7 +174,7 @@ Now you can record a dataset. To record 5 episodes and upload your dataset to th
 <hfoptions id="record">
 <hfoption id="Command">
 ```bash
-lerobot-record \
+python -m lerobot.record \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem585A0076841 \
     --robot.id=my_awesome_follower_arm \
@@ -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/${HF_USER}/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/cadene/so101_test) that you can obtain by running:
 
 ```bash
 echo https://huggingface.co/datasets/${HF_USER}/so101_test
@@ -376,7 +376,7 @@ You can replay the first episode on your robot with either the command below or
 <hfoptions id="replay">
 <hfoption id="Command">
 ```bash
-lerobot-replay \
+python -m lerobot.replay \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.id=my_awesome_follower_arm \
@@ -428,10 +428,10 @@ 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 [`lerobot-train`](https://github.com/huggingface/lerobot/blob/main/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`](../src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --dataset.repo_id=${HF_USER}/so101_test \
   --policy.type=act \
   --output_dir=outputs/train/act_so101_test \
@@ -444,7 +444,7 @@ lerobot-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`](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.
+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.
 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`.
 
@@ -453,7 +453,7 @@ Training should take several hours. You will find checkpoints in `outputs/train/
 To resume training from a checkpoint, below is an example command to resume from `last` checkpoint of the `act_so101_test` policy:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --config_path=outputs/train/act_so101_test/checkpoints/last/pretrained_model/train_config.json \
   --resume=true
 ```
@@ -490,7 +490,7 @@ You can use the `record` script from [`lerobot/record.py`](https://github.com/hu
 <hfoptions id="eval">
 <hfoption id="Command">
 ```bash
-lerobot-record  \
+python -m lerobot.record  \
   --robot.type=so100_follower \
   --robot.port=/dev/ttyACM1 \
   --robot.cameras="{ up: {type: opencv, index_or_path: /dev/video10, width: 640, height: 480, fps: 30}, side: {type: intelrealsense, serial_number_or_name: 233522074606, width: 640, height: 480, fps: 30}}" \

docs/source/il_sim.mdx

@@ -96,10 +96,10 @@ 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 [`lerobot-train`](https://github.com/huggingface/lerobot/blob/main/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`](../src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --dataset.repo_id=${HF_USER}/il_gym \
   --policy.type=act \
   --output_dir=outputs/train/il_sim_test \
@@ -111,7 +111,7 @@ lerobot-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`](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.
+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.
 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/installation.mdx

@@ -1,6 +1,15 @@
 # Installation
 
-## Environment Setup
+## Install LeRobot
+
+Currently only available from source.
+
+Download our source code:
+
+```bash
+git clone https://github.com/huggingface/lerobot.git
+cd lerobot
+```
 
 Create a virtual environment with Python 3.10, using [`Miniconda`](https://docs.anaconda.com/miniconda/install/#quick-command-line-install)
 
@@ -31,49 +40,12 @@ conda install ffmpeg -c conda-forge
 >
 > - _[On Linux only]_ If you want to bring your own ffmpeg: Install [ffmpeg build dependencies](https://trac.ffmpeg.org/wiki/CompilationGuide/Ubuntu#GettheDependencies) and [compile ffmpeg from source with libsvtav1](https://trac.ffmpeg.org/wiki/CompilationGuide/Ubuntu#libsvtav1), and make sure you use the corresponding ffmpeg binary to your install with `which ffmpeg`.
 
-## Install LeRobot 🤗
-
-### From Source
-
-First, clone the repository and navigate into the directory:
-
-```bash
-git clone https://github.com/huggingface/lerobot.git
-cd lerobot
-```
-
-Then, install the library in editable mode. This is useful if you plan to contribute to the code.
+Install 🤗 LeRobot:
 
 ```bash
 pip install -e .
 ```
 
-### Installation from PyPI
-
-**Core Library:**
-Install the base package with:
-
-```bash
-pip install lerobot
-```
-
-_This installs only the default dependencies._
-
-**Extra Features:**
-To install additional functionality, use one of the following:
-
-```bash
-pip install 'lerobot[all]'          # All available features
-pip install 'lerobot[aloha,pusht]'  # Specific features (Aloha & Pusht)
-pip install 'lerobot[feetech]'      # Feetech motor support
-```
-
-_Replace `[...]` with your desired features._
-
-**Available Tags:**
-For a full list of optional dependencies, see:
-https://pypi.org/project/lerobot/
-
 ### Troubleshooting
 
 If you encounter build errors, you may need to install additional dependencies: `cmake`, `build-essential`, and `ffmpeg libs`.

docs/source/koch.mdx

@@ -31,7 +31,7 @@ pip install -e ".[dynamixel]"
 To find the port for each bus servo adapter, run this script:
 
 ```bash
-lerobot-find-port
+python -m lerobot.find_port
 ```
 
 <hfoptions id="example">
@@ -98,7 +98,7 @@ For a visual reference on how to set the motor ids please refer to [this video](
 <hfoption id="Command">
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --robot.type=koch_follower \
     --robot.port=/dev/tty.usbmodem575E0031751 # <- paste here the port found at previous step
 ```
@@ -174,7 +174,7 @@ Do the same steps for the leader arm but modify the command or script accordingl
 <hfoption id="Command">
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --teleop.type=koch_leader \
     --teleop.port=/dev/tty.usbmodem575E0031751 \  # <- paste here the port found at previous step
 ```
@@ -211,7 +211,7 @@ Run the following command or API example to calibrate the follower arm:
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=koch_follower \
     --robot.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --robot.id=my_awesome_follower_arm  # <- Give the robot a unique name
@@ -249,7 +249,7 @@ Do the same steps to calibrate the leader arm, run the following command or API
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=koch_leader \
     --teleop.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --teleop.id=my_awesome_leader_arm  # <- Give the robot a unique name

docs/source/lekiwi.mdx

@@ -60,7 +60,7 @@ First, we will assemble the two SO100/SO101 arms. One to attach to the mobile ba
 To find the port for each bus servo adapter, run this script:
 
 ```bash
-lerobot-find-port
+python -m lerobot.find_port
 ```
 
 <hfoptions id="example">
@@ -116,7 +116,7 @@ The instructions for configuring the motors can be found in the SO101 [docs](./s
 You can run this command to setup motors for LeKiwi. It will first setup the motors for arm (id 6..1) and then setup motors for wheels (9,8,7)
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --robot.type=lekiwi \
     --robot.port=/dev/tty.usbmodem58760431551 # <- paste here the port found at previous step
 ```
@@ -174,7 +174,7 @@ The calibration process is very important because it allows a neural network tra
 Make sure the arm is connected to the Raspberry Pi and run this script or API example (on the Raspberry Pi via SSH) to launch calibration of the follower arm:
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=lekiwi \
     --robot.id=my_awesome_kiwi # <- Give the robot a unique name
 ```
@@ -193,7 +193,7 @@ Then, to calibrate the leader arm (which is attached to the laptop/pc). Run the
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=so100_leader \
     --teleop.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --teleop.id=my_awesome_leader_arm # <- Give the robot a unique name

docs/source/policy_act_README.md

@@ -1,14 +0,0 @@
-## 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_diffusion_README.md

@@ -1,14 +0,0 @@
-## 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_smolvla_README.md

@@ -1,14 +0,0 @@
-## 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_tdmpc_README.md

@@ -1,14 +0,0 @@
-## 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}
-}
-```

docs/source/policy_vqbet_README.md

@@ -1,14 +0,0 @@
-## Paper
-
-https://sjlee.cc/vq-bet/
-
-## Citation
-
-```bibtex
-@article{lee2024behavior,
-  title={Behavior generation with latent actions},
-  author={Lee, Seungjae and Wang, Yibin and Etukuru, Haritheja and Kim, H Jin and Shafiullah, Nur Muhammad Mahi and Pinto, Lerrel},
-  journal={arXiv preprint arXiv:2403.03181},
-  year={2024}
-}
-```

docs/source/smolvla.mdx

@@ -54,7 +54,7 @@ If you don't have a gpu device, you can train using our notebook on [![Google Co
 Pass your dataset to the training script using `--dataset.repo_id`. If you want to test your installation, run the following command where we use one of the datasets we collected for the [SmolVLA Paper](https://huggingface.co/papers/2506.01844).
 
 ```bash
-cd lerobot && lerobot-train \
+cd lerobot && python -m lerobot.scripts.train \
   --policy.path=lerobot/smolvla_base \
   --dataset.repo_id=${HF_USER}/mydataset \
   --batch_size=64 \
@@ -73,7 +73,7 @@ cd lerobot && lerobot-train \
 Fine-tuning is an art. For a complete overview of the options for finetuning, run
 
 ```bash
-lerobot-train --help
+python -m lerobot.scripts.train --help
 ```
 
 <p align="center">
@@ -97,7 +97,7 @@ Similarly for when recording an episode, it is recommended that you are logged i
 Once you are logged in, you can run inference in your setup by doing:
 
 ```bash
-lerobot-record \
+python -m lerobot.record \
   --robot.type=so101_follower \
   --robot.port=/dev/ttyACM0 \ # <- Use your port
   --robot.id=my_blue_follower_arm \ # <- Use your robot id

docs/source/so100.mdx

@@ -26,7 +26,7 @@ Unlike the SO-101, the motor connectors are not easily accessible once the arm i
 To find the port for each bus servo adapter, run this script:
 
 ```bash
-lerobot-find-port
+python -m lerobot.find_port
 ```
 
 <hfoptions id="example">
@@ -93,7 +93,7 @@ For a visual reference on how to set the motor ids please refer to [this video](
 <hfoption id="Command">
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem585A0076841  # <- paste here the port found at previous step
 ```
@@ -168,7 +168,7 @@ Do the same steps for the leader arm.
 <hfoptions id="setup_motors">
 <hfoption id="Command">
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --teleop.type=so100_leader \
     --teleop.port=/dev/tty.usbmodem575E0031751  # <- paste here the port found at previous step
 ```
@@ -568,7 +568,7 @@ Run the following command or API example to calibrate the follower arm:
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --robot.id=my_awesome_follower_arm # <- Give the robot a unique name
@@ -606,7 +606,7 @@ Do the same steps to calibrate the leader arm, run the following command or API
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=so100_leader \
     --teleop.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --teleop.id=my_awesome_leader_arm # <- Give the robot a unique name

docs/source/so101.mdx

@@ -162,7 +162,7 @@ It is advisable to install one 3-pin cable in the motor after placing them befor
 To find the port for each bus servo adapter, connect MotorBus to your computer via USB and power. Run the following script and disconnect the MotorBus when prompted:
 
 ```bash
-lerobot-find-port
+python -m lerobot.find_port
 ```
 
 <hfoptions id="example">
@@ -240,7 +240,7 @@ Connect the usb cable from your computer and the power supply to the follower ar
 <hfoption id="Command">
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem585A0076841  # <- paste here the port found at previous step
 ```
@@ -316,7 +316,7 @@ Do the same steps for the leader arm.
 <hfoption id="Command">
 
 ```bash
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --teleop.type=so101_leader \
     --teleop.port=/dev/tty.usbmodem575E0031751  # <- paste here the port found at previous step
 ```
@@ -353,7 +353,7 @@ Run the following command or API example to calibrate the follower arm:
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --robot.id=my_awesome_follower_arm # <- Give the robot a unique name
@@ -402,7 +402,7 @@ Do the same steps to calibrate the leader arm, run the following command or API
 <hfoption id="Command">
 
 ```bash
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=so101_leader \
     --teleop.port=/dev/tty.usbmodem58760431551 \ # <- The port of your robot
     --teleop.id=my_awesome_leader_arm # <- Give the robot a unique name

examples/4_train_policy_with_script.md

@@ -62,7 +62,7 @@ By default, every field takes its default value specified in the dataclass. If a
 Let's say that we want to train [Diffusion Policy](../src/lerobot/policies/diffusion) on the [pusht](https://huggingface.co/datasets/lerobot/pusht) dataset, using the [gym_pusht](https://github.com/huggingface/gym-pusht) environment for evaluation. The command to do so would look like this:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --dataset.repo_id=lerobot/pusht \
     --policy.type=diffusion \
     --env.type=pusht
@@ -77,7 +77,7 @@ Let's break this down:
 Let's see another example. Let's say you've been training [ACT](../src/lerobot/policies/act) on [lerobot/aloha_sim_insertion_human](https://huggingface.co/datasets/lerobot/aloha_sim_insertion_human) using the [gym-aloha](https://github.com/huggingface/gym-aloha) environment for evaluation with:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.type=act \
     --dataset.repo_id=lerobot/aloha_sim_insertion_human \
     --env.type=aloha \
@@ -90,7 +90,7 @@ We now want to train a different policy for aloha on another task. We'll change
 Looking at the [`AlohaEnv`](../src/lerobot/envs/configs.py) config, the task is `"AlohaInsertion-v0"` by default, which corresponds to the task we trained on in the command above. The [gym-aloha](https://github.com/huggingface/gym-aloha?tab=readme-ov-file#description) environment also has the `AlohaTransferCube-v0` task which corresponds to this other task we want to train on. Putting this together, we can train this new policy on this different task using:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.type=act \
     --dataset.repo_id=lerobot/aloha_sim_transfer_cube_human \
     --env.type=aloha \
@@ -127,7 +127,7 @@ Now, let's assume that we want to reproduce the run just above. That run has pro
 We can then simply load the config values from this file using:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=outputs/train/act_aloha_transfer/checkpoints/last/pretrained_model/ \
     --output_dir=outputs/train/act_aloha_transfer_2
 ```
@@ -137,7 +137,7 @@ lerobot-train \
 Similarly to Hydra, we can still override some parameters in the CLI if we want to, e.g.:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=outputs/train/act_aloha_transfer/checkpoints/last/pretrained_model/ \
     --output_dir=outputs/train/act_aloha_transfer_2
     --policy.n_action_steps=80
@@ -148,7 +148,7 @@ lerobot-train \
 `--config_path` can also accept the repo_id of a repo on the hub that contains a `train_config.json` file, e.g. running:
 
 ```bash
-lerobot-train --config_path=lerobot/diffusion_pusht
+python -m lerobot.scripts.train --config_path=lerobot/diffusion_pusht
 ```
 
 will start a training run with the same configuration used for training [lerobot/diffusion_pusht](https://huggingface.co/lerobot/diffusion_pusht)
@@ -160,7 +160,7 @@ Being able to resume a training run is important in case it crashed or aborted f
 Let's reuse the command from the previous run and add a few more options:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.type=act \
     --dataset.repo_id=lerobot/aloha_sim_transfer_cube_human \
     --env.type=aloha \
@@ -179,7 +179,7 @@ INFO 2025-01-24 16:10:56 ts/train.py:263 Checkpoint policy after step 100
 Now let's simulate a crash by killing the process (hit `ctrl`+`c`). We can then simply resume this run from the last checkpoint available with:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=outputs/train/run_resumption/checkpoints/last/pretrained_model/ \
     --resume=true
 ```
@@ -190,7 +190,7 @@ Another reason for which you might want to resume a run is simply to extend trai
 You could double the number of steps of the previous run with:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=outputs/train/run_resumption/checkpoints/last/pretrained_model/ \
     --resume=true \
     --steps=200000
@@ -224,7 +224,7 @@ In addition to the features currently in Draccus, we've added a special `.path`
 For example, we could fine-tune a [policy pre-trained on the aloha transfer task](https://huggingface.co/lerobot/act_aloha_sim_transfer_cube_human) on the aloha insertion task. We can achieve this with:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.path=lerobot/act_aloha_sim_transfer_cube_human \
     --dataset.repo_id=lerobot/aloha_sim_insertion_human \
     --env.type=aloha \
@@ -270,7 +270,7 @@ We'll summarize here the main use cases to remember from this tutorial.
 #### Train a policy from scratch – CLI
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.type=act \  # <- select 'act' policy
     --env.type=pusht \  # <- select 'pusht' environment
     --dataset.repo_id=lerobot/pusht  # <- train on this dataset
@@ -279,7 +279,7 @@ lerobot-train \
 #### Train a policy from scratch - config file + CLI
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=path/to/pretrained_model \  # <- can also be a repo_id
     --policy.n_action_steps=80  # <- you may still override values
 ```
@@ -287,7 +287,7 @@ lerobot-train \
 #### Resume/continue a training run
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --config_path=checkpoint/pretrained_model/ \
     --resume=true \
     --steps=200000  # <- you can change some training parameters
@@ -296,7 +296,7 @@ lerobot-train \
 #### Fine-tuning
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
     --policy.path=lerobot/act_aloha_sim_transfer_cube_human \  # <- can also be a local path to a checkpoint
     --dataset.repo_id=lerobot/aloha_sim_insertion_human \
     --env.type=aloha \

examples/backward_compatibility/replay.py

@@ -18,7 +18,7 @@ Replays the actions of an episode from a dataset on a robot.
 Example:
 
 ```shell
-lerobot-replay \
+python -m lerobot.replay \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.id=black \

pyproject.toml

@@ -25,7 +25,7 @@ discord = "https://discord.gg/s3KuuzsPFb"
 
 [project]
 name = "lerobot"
-version = "0.3.4"
+version = "0.2.0"
 description = "🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch"
 readme = "README.md"
 license = { text = "Apache-2.0" }
@@ -68,16 +68,15 @@ dependencies = [
     "einops>=0.8.0",
     "opencv-python-headless>=4.9.0",
     "av>=14.2.0",
+    "torch>=2.2.1",
+    "torchcodec>=0.2.1; sys_platform != 'win32' and (sys_platform != 'linux' or (platform_machine != 'aarch64' and platform_machine != 'arm64' and platform_machine != 'armv7l')) and (sys_platform != 'darwin' or platform_machine != 'x86_64')",
+    "torchvision>=0.21.0",
     "jsonlines>=4.0.0",
     "packaging>=24.2",
     "pynput>=1.7.7",
     "pyserial>=3.5",
     "wandb>=0.20.0",
 
-    "torch>=2.2.1,<2.8.0", # TODO: Bumb dependency
-    "torchcodec>=0.2.1,<0.6.0; sys_platform != 'win32' and (sys_platform != 'linux' or (platform_machine != 'aarch64' and platform_machine != 'arm64' and platform_machine != 'armv7l')) and (sys_platform != 'darwin' or platform_machine != 'x86_64')", # TODO: Bumb dependency
-    "torchvision>=0.21.0,<0.23.0", # TODO: Bumb dependency
-
     "draccus==0.10.0", # TODO: Remove ==
     "gymnasium>=0.29.1,<1.0.0", # TODO: Bumb dependency
     "rerun-sdk>=0.21.0,<0.23.0", # TODO: Bumb dependency
@@ -126,6 +125,7 @@ hilserl = ["lerobot[transformers-dep]", "gym-hil>=0.1.9", "lerobot[grpcio-dep]",
 async = ["lerobot[grpcio-dep]", "matplotlib>=3.10.3"]
 
 # Development
+docs = ["hf-doc-builder @ git+https://github.com/huggingface/doc-builder.git@main", "watchdog >= 6.0.0"]
 dev = ["pre-commit>=3.7.0", "debugpy>=1.8.1", "lerobot[grpcio-dep]", "grpcio-tools==1.73.1"]
 test = ["pytest>=8.1.0", "pytest-timeout>=2.4.0", "pytest-cov>=5.0.0", "mock-serial>=0.0.1 ; sys_platform != 'win32'"]
 video_benchmark = ["scikit-image>=0.23.2", "pandas>=2.2.2"]
@@ -147,6 +147,7 @@ all = [
     "lerobot[smolvla]",
     "lerobot[hilserl]",
     "lerobot[async]",
+    "lerobot[docs]",
     "lerobot[dev]",
     "lerobot[test]",
     "lerobot[video_benchmark]",

requirements-macos.txt

@@ -1,625 +0,0 @@
-# This file is autogenerated by pip-compile with Python 3.10
-# by the following command:
-#
-#    pip-compile --output-file=requirements-macos.txt requirements.in
-#
--e .[all]
-    # via -[all]
-absl-py==2.3.1
-    # via
-    #   dm-control
-    #   dm-env
-    #   dm-tree
-    #   labmaze
-    #   mujoco
-accelerate==1.9.0
-    # via lerobot
-aiohappyeyeballs==2.6.1
-    # via aiohttp
-aiohttp==3.12.15
-    # via fsspec
-aiosignal==1.4.0
-    # via aiohttp
-annotated-types==0.7.0
-    # via pydantic
-asttokens==3.0.0
-    # via stack-data
-async-timeout==5.0.1
-    # via aiohttp
-attrs==25.3.0
-    # via
-    #   aiohttp
-    #   dm-tree
-    #   jsonlines
-    #   rerun-sdk
-av==15.0.0
-    # via lerobot
-blinker==1.9.0
-    # via flask
-certifi==2025.7.14
-    # via
-    #   requests
-    #   sentry-sdk
-cffi==1.17.1
-    # via pymunk
-cfgv==3.4.0
-    # via pre-commit
-charset-normalizer==3.4.2
-    # via requests
-click==8.2.1
-    # via
-    #   flask
-    #   wandb
-cloudpickle==3.1.1
-    # via gymnasium
-cmake==4.0.3
-    # via lerobot
-cmeel==0.57.3
-    # via
-    #   cmeel-assimp
-    #   cmeel-boost
-    #   cmeel-console-bridge
-    #   cmeel-octomap
-    #   cmeel-qhull
-    #   cmeel-tinyxml2
-    #   cmeel-urdfdom
-    #   cmeel-zlib
-    #   coal-library
-    #   eigenpy
-    #   eiquadprog
-    #   pin
-    #   placo
-    #   rhoban-cmeel-jsoncpp
-cmeel-assimp==5.4.3.1
-    # via coal-library
-cmeel-boost==1.87.0.1
-    # via
-    #   coal-library
-    #   eigenpy
-    #   eiquadprog
-    #   pin
-cmeel-console-bridge==1.0.2.3
-    # via cmeel-urdfdom
-cmeel-octomap==1.10.0
-    # via coal-library
-cmeel-qhull==8.0.2.1
-    # via coal-library
-cmeel-tinyxml2==10.0.0
-    # via cmeel-urdfdom
-cmeel-urdfdom==4.0.1
-    # via pin
-cmeel-zlib==1.3.1
-    # via cmeel-assimp
-coal-library==3.0.1
-    # via pin
-contourpy==1.3.2
-    # via matplotlib
-coverage[toml]==7.10.1
-    # via pytest-cov
-cycler==0.12.1
-    # via matplotlib
-datasets==3.6.0
-    # via lerobot
-debugpy==1.8.15
-    # via lerobot
-decorator==5.2.1
-    # via ipython
-deepdiff==8.5.0
-    # via lerobot
-diffusers==0.34.0
-    # via lerobot
-dill==0.3.8
-    # via
-    #   datasets
-    #   multiprocess
-distlib==0.4.0
-    # via virtualenv
-dm-control==1.0.14
-    # via gym-aloha
-dm-env==1.6
-    # via dm-control
-dm-tree==0.1.9
-    # via
-    #   dm-control
-    #   dm-env
-docopt==0.6.2
-    # via num2words
-draccus==0.10.0
-    # via lerobot
-dynamixel-sdk==3.7.31
-    # via lerobot
-eigenpy==3.10.3
-    # via coal-library
-einops==0.8.1
-    # via lerobot
-eiquadprog==1.2.9
-    # via placo
-exceptiongroup==1.3.0
-    # via
-    #   ipython
-    #   pytest
-executing==2.2.0
-    # via stack-data
-farama-notifications==0.0.4
-    # via gymnasium
-feetech-servo-sdk==1.0.0
-    # via lerobot
-filelock==3.18.0
-    # via
-    #   datasets
-    #   diffusers
-    #   huggingface-hub
-    #   torch
-    #   transformers
-    #   virtualenv
-flask==3.1.1
-    # via lerobot
-fonttools==4.59.0
-    # via matplotlib
-frozenlist==1.7.0
-    # via
-    #   aiohttp
-    #   aiosignal
-fsspec[http]==2025.3.0
-    # via
-    #   datasets
-    #   huggingface-hub
-    #   torch
-gitdb==4.0.12
-    # via gitpython
-gitpython==3.1.45
-    # via wandb
-glfw==2.9.0
-    # via
-    #   dm-control
-    #   mujoco
-grpcio==1.73.1
-    # via
-    #   grpcio-tools
-    #   lerobot
-grpcio-tools==1.73.1
-    # via lerobot
-gym-aloha==0.1.1
-    # via lerobot
-gym-hil==0.1.10
-    # via lerobot
-gym-pusht==0.1.5
-    # via lerobot
-gym-xarm==0.1.1
-    # via lerobot
-gymnasium==0.29.1
-    # via
-    #   gym-aloha
-    #   gym-hil
-    #   gym-pusht
-    #   gym-xarm
-    #   gymnasium-robotics
-    #   lerobot
-    #   pettingzoo
-gymnasium-robotics==1.2.4
-    # via gym-xarm
-hf-transfer==0.1.9
-    # via huggingface-hub
-hf-xet==1.1.5
-    # via huggingface-hub
-hidapi==0.14.0.post4
-    # via
-    #   gym-hil
-    #   lerobot
-huggingface-hub[cli,hf-transfer]==0.34.3
-    # via
-    #   accelerate
-    #   datasets
-    #   diffusers
-    #   lerobot
-    #   tokenizers
-    #   transformers
-identify==2.6.12
-    # via pre-commit
-idna==3.10
-    # via
-    #   requests
-    #   yarl
-imageio[ffmpeg]==2.37.0
-    # via
-    #   gym-aloha
-    #   gym-hil
-    #   gymnasium-robotics
-    #   lerobot
-    #   scikit-image
-imageio-ffmpeg==0.6.0
-    # via imageio
-importlib-metadata==8.7.0
-    # via diffusers
-iniconfig==2.1.0
-    # via pytest
-inquirerpy==0.3.4
-    # via huggingface-hub
-ipython==8.37.0
-    # via meshcat
-ischedule==1.2.7
-    # via placo
-itsdangerous==2.2.0
-    # via flask
-jedi==0.19.2
-    # via ipython
-jinja2==3.1.6
-    # via
-    #   flask
-    #   gymnasium-robotics
-    #   torch
-jsonlines==4.0.0
-    # via lerobot
-kiwisolver==1.4.8
-    # via matplotlib
-labmaze==1.0.6
-    # via dm-control
-lazy-loader==0.4
-    # via scikit-image
-lxml==6.0.0
-    # via dm-control
-markupsafe==3.0.2
-    # via
-    #   flask
-    #   jinja2
-    #   werkzeug
-matplotlib==3.10.5
-    # via lerobot
-matplotlib-inline==0.1.7
-    # via ipython
-mergedeep==1.3.4
-    # via draccus
-meshcat==0.3.2
-    # via placo
-mock-serial==0.0.1
-    # via lerobot
-mpmath==1.3.0
-    # via sympy
-mujoco==2.3.7
-    # via
-    #   dm-control
-    #   gym-aloha
-    #   gym-hil
-    #   gym-xarm
-    #   gymnasium-robotics
-multidict==6.6.3
-    # via
-    #   aiohttp
-    #   yarl
-multiprocess==0.70.16
-    # via datasets
-mypy-extensions==1.1.0
-    # via typing-inspect
-networkx==3.4.2
-    # via
-    #   scikit-image
-    #   torch
-nodeenv==1.9.1
-    # via pre-commit
-num2words==0.5.14
-    # via lerobot
-numpy==2.2.6
-    # via
-    #   accelerate
-    #   cmeel-boost
-    #   contourpy
-    #   datasets
-    #   diffusers
-    #   dm-control
-    #   dm-env
-    #   dm-tree
-    #   gymnasium
-    #   gymnasium-robotics
-    #   imageio
-    #   labmaze
-    #   matplotlib
-    #   meshcat
-    #   mujoco
-    #   opencv-python
-    #   opencv-python-headless
-    #   pandas
-    #   pettingzoo
-    #   rerun-sdk
-    #   scikit-image
-    #   scipy
-    #   shapely
-    #   tifffile
-    #   torchvision
-    #   transformers
-opencv-python==4.12.0.88
-    # via gym-pusht
-opencv-python-headless==4.12.0.88
-    # via lerobot
-orderly-set==5.5.0
-    # via deepdiff
-packaging==25.0
-    # via
-    #   accelerate
-    #   datasets
-    #   huggingface-hub
-    #   lazy-loader
-    #   lerobot
-    #   matplotlib
-    #   pytest
-    #   scikit-image
-    #   transformers
-    #   wandb
-pandas==2.3.1
-    # via
-    #   datasets
-    #   lerobot
-parso==0.8.4
-    # via jedi
-pettingzoo==1.24.3
-    # via gymnasium-robotics
-pexpect==4.9.0
-    # via ipython
-pfzy==0.3.4
-    # via inquirerpy
-pillow==11.3.0
-    # via
-    #   diffusers
-    #   imageio
-    #   matplotlib
-    #   meshcat
-    #   rerun-sdk
-    #   scikit-image
-    #   torchvision
-pin==3.4.0
-    # via placo
-placo==0.9.14
-    # via lerobot
-platformdirs==4.3.8
-    # via
-    #   virtualenv
-    #   wandb
-pluggy==1.6.0
-    # via
-    #   pytest
-    #   pytest-cov
-pre-commit==4.2.0
-    # via lerobot
-prompt-toolkit==3.0.51
-    # via
-    #   inquirerpy
-    #   ipython
-propcache==0.3.2
-    # via
-    #   aiohttp
-    #   yarl
-protobuf==6.31.0
-    # via
-    #   dm-control
-    #   grpcio-tools
-    #   lerobot
-    #   wandb
-psutil==7.0.0
-    # via
-    #   accelerate
-    #   imageio
-ptyprocess==0.7.0
-    # via pexpect
-pure-eval==0.2.3
-    # via stack-data
-pyarrow==21.0.0
-    # via
-    #   datasets
-    #   rerun-sdk
-pycparser==2.22
-    # via cffi
-pydantic==2.11.7
-    # via wandb
-pydantic-core==2.33.2
-    # via pydantic
-pygame==2.6.1
-    # via
-    #   gym-hil
-    #   gym-pusht
-    #   lerobot
-pygments==2.19.2
-    # via
-    #   ipython
-    #   pytest
-pymunk==6.11.1
-    # via
-    #   gym-pusht
-    #   lerobot
-pyngrok==7.2.12
-    # via meshcat
-pynput==1.8.1
-    # via
-    #   gym-hil
-    #   lerobot
-pyobjc-core==11.1
-    # via
-    #   pyobjc-framework-applicationservices
-    #   pyobjc-framework-cocoa
-    #   pyobjc-framework-coretext
-    #   pyobjc-framework-quartz
-pyobjc-framework-applicationservices==11.1
-    # via pynput
-pyobjc-framework-cocoa==11.1
-    # via
-    #   pyobjc-framework-applicationservices
-    #   pyobjc-framework-coretext
-    #   pyobjc-framework-quartz
-pyobjc-framework-coretext==11.1
-    # via pyobjc-framework-applicationservices
-pyobjc-framework-quartz==11.1
-    # via
-    #   pynput
-    #   pyobjc-framework-applicationservices
-    #   pyobjc-framework-coretext
-pyopengl==3.1.9
-    # via
-    #   dm-control
-    #   mujoco
-pyparsing==3.2.3
-    # via
-    #   dm-control
-    #   matplotlib
-pyrealsense2-macosx==2.54.2
-    # via lerobot
-pyserial==3.5
-    # via
-    #   dynamixel-sdk
-    #   feetech-servo-sdk
-    #   lerobot
-pytest==8.4.1
-    # via
-    #   lerobot
-    #   pytest-cov
-    #   pytest-timeout
-pytest-cov==6.2.1
-    # via lerobot
-pytest-timeout==2.4.0
-    # via lerobot
-python-dateutil==2.9.0.post0
-    # via
-    #   matplotlib
-    #   pandas
-pytz==2025.2
-    # via pandas
-pyyaml==6.0.2
-    # via
-    #   accelerate
-    #   datasets
-    #   draccus
-    #   huggingface-hub
-    #   pre-commit
-    #   pyngrok
-    #   pyyaml-include
-    #   transformers
-    #   wandb
-pyyaml-include==1.4.1
-    # via draccus
-pyzmq==27.0.0
-    # via
-    #   lerobot
-    #   meshcat
-regex==2025.7.34
-    # via
-    #   diffusers
-    #   transformers
-requests==2.32.4
-    # via
-    #   datasets
-    #   diffusers
-    #   dm-control
-    #   huggingface-hub
-    #   transformers
-    #   wandb
-rerun-sdk==0.22.1
-    # via lerobot
-rhoban-cmeel-jsoncpp==1.9.4.9
-    # via placo
-safetensors==0.5.3
-    # via
-    #   accelerate
-    #   diffusers
-    #   lerobot
-    #   transformers
-scikit-image==0.25.2
-    # via
-    #   gym-pusht
-    #   lerobot
-scipy==1.15.3
-    # via
-    #   dm-control
-    #   scikit-image
-sentry-sdk==2.34.1
-    # via wandb
-shapely==2.1.1
-    # via gym-pusht
-six==1.17.0
-    # via
-    #   pynput
-    #   python-dateutil
-smmap==5.0.2
-    # via gitdb
-stack-data==0.6.3
-    # via ipython
-sympy==1.14.0
-    # via torch
-termcolor==3.1.0
-    # via lerobot
-tifffile==2025.5.10
-    # via scikit-image
-tokenizers==0.21.4
-    # via transformers
-toml==0.10.2
-    # via draccus
-tomli==2.2.1
-    # via
-    #   cmeel
-    #   coverage
-    #   pytest
-torch==2.7.1
-    # via
-    #   accelerate
-    #   lerobot
-    #   torchvision
-torchcodec==0.5
-    # via lerobot
-torchvision==0.22.1
-    # via lerobot
-tornado==6.5.1
-    # via meshcat
-tqdm==4.67.1
-    # via
-    #   datasets
-    #   dm-control
-    #   huggingface-hub
-    #   transformers
-traitlets==5.14.3
-    # via
-    #   ipython
-    #   matplotlib-inline
-transformers==4.51.3
-    # via lerobot
-typing-extensions==4.14.1
-    # via
-    #   aiosignal
-    #   exceptiongroup
-    #   gymnasium
-    #   huggingface-hub
-    #   ipython
-    #   multidict
-    #   pydantic
-    #   pydantic-core
-    #   rerun-sdk
-    #   torch
-    #   typing-inspect
-    #   typing-inspection
-    #   wandb
-typing-inspect==0.9.0
-    # via draccus
-typing-inspection==0.4.1
-    # via pydantic
-tzdata==2025.2
-    # via pandas
-u-msgpack-python==2.8.0
-    # via meshcat
-urllib3==2.5.0
-    # via
-    #   requests
-    #   sentry-sdk
-virtualenv==20.32.0
-    # via pre-commit
-wandb==0.21.0
-    # via lerobot
-wcwidth==0.2.13
-    # via prompt-toolkit
-werkzeug==3.1.3
-    # via flask
-wrapt==1.17.2
-    # via dm-tree
-xxhash==3.5.0
-    # via datasets
-yarl==1.20.1
-    # via aiohttp
-zipp==3.23.0
-    # via importlib-metadata
-
-# The following packages are considered to be unsafe in a requirements file:
-# setuptools

requirements-ubuntu.txt

@@ -1,650 +0,0 @@
-#
-# This file is autogenerated by pip-compile with Python 3.10
-# by the following command:
-#
-#    pip-compile --output-file=requirements-ubuntu.txt requirements.in
-#
--e .[all]
-    # via -[all]
-absl-py==2.3.1
-    # via
-    #   dm-control
-    #   dm-env
-    #   dm-tree
-    #   labmaze
-    #   mujoco
-accelerate==1.9.0
-    # via lerobot
-aiohappyeyeballs==2.6.1
-    # via aiohttp
-aiohttp==3.12.15
-    # via fsspec
-aiosignal==1.4.0
-    # via aiohttp
-annotated-types==0.7.0
-    # via pydantic
-asttokens==3.0.0
-    # via stack-data
-async-timeout==5.0.1
-    # via aiohttp
-attrs==25.3.0
-    # via
-    #   aiohttp
-    #   dm-tree
-    #   jsonlines
-    #   rerun-sdk
-av==15.0.0
-    # via lerobot
-blinker==1.9.0
-    # via flask
-certifi==2025.7.14
-    # via
-    #   requests
-    #   sentry-sdk
-cffi==1.17.1
-    # via pymunk
-cfgv==3.4.0
-    # via pre-commit
-charset-normalizer==3.4.2
-    # via requests
-click==8.2.1
-    # via
-    #   flask
-    #   wandb
-cloudpickle==3.1.1
-    # via gymnasium
-cmake==4.0.3
-    # via lerobot
-cmeel==0.57.3
-    # via
-    #   cmeel-assimp
-    #   cmeel-boost
-    #   cmeel-console-bridge
-    #   cmeel-octomap
-    #   cmeel-qhull
-    #   cmeel-tinyxml2
-    #   cmeel-urdfdom
-    #   cmeel-zlib
-    #   coal-library
-    #   eigenpy
-    #   eiquadprog
-    #   pin
-    #   placo
-    #   rhoban-cmeel-jsoncpp
-cmeel-assimp==5.4.3.1
-    # via coal-library
-cmeel-boost==1.87.0.1
-    # via
-    #   coal-library
-    #   eigenpy
-    #   eiquadprog
-    #   pin
-cmeel-console-bridge==1.0.2.3
-    # via cmeel-urdfdom
-cmeel-octomap==1.10.0
-    # via coal-library
-cmeel-qhull==8.0.2.1
-    # via coal-library
-cmeel-tinyxml2==10.0.0
-    # via cmeel-urdfdom
-cmeel-urdfdom==4.0.1
-    # via pin
-cmeel-zlib==1.3.1
-    # via cmeel-assimp
-coal-library==3.0.1
-    # via pin
-contourpy==1.3.2
-    # via matplotlib
-coverage[toml]==7.10.1
-    # via pytest-cov
-cycler==0.12.1
-    # via matplotlib
-datasets==3.6.0
-    # via lerobot
-debugpy==1.8.15
-    # via lerobot
-decorator==5.2.1
-    # via ipython
-deepdiff==8.5.0
-    # via lerobot
-diffusers==0.34.0
-    # via lerobot
-dill==0.3.8
-    # via
-    #   datasets
-    #   multiprocess
-distlib==0.4.0
-    # via virtualenv
-dm-control==1.0.14
-    # via gym-aloha
-dm-env==1.6
-    # via dm-control
-dm-tree==0.1.9
-    # via
-    #   dm-control
-    #   dm-env
-docopt==0.6.2
-    # via num2words
-draccus==0.10.0
-    # via lerobot
-dynamixel-sdk==3.7.31
-    # via lerobot
-eigenpy==3.10.3
-    # via coal-library
-einops==0.8.1
-    # via lerobot
-eiquadprog==1.2.9
-    # via placo
-evdev==1.9.2
-    # via pynput
-exceptiongroup==1.3.0
-    # via
-    #   ipython
-    #   pytest
-executing==2.2.0
-    # via stack-data
-farama-notifications==0.0.4
-    # via gymnasium
-feetech-servo-sdk==1.0.0
-    # via lerobot
-filelock==3.18.0
-    # via
-    #   datasets
-    #   diffusers
-    #   huggingface-hub
-    #   torch
-    #   transformers
-    #   virtualenv
-flask==3.1.1
-    # via lerobot
-fonttools==4.59.0
-    # via matplotlib
-frozenlist==1.7.0
-    # via
-    #   aiohttp
-    #   aiosignal
-fsspec[http]==2025.3.0
-    # via
-    #   datasets
-    #   huggingface-hub
-    #   torch
-gitdb==4.0.12
-    # via gitpython
-gitpython==3.1.45
-    # via wandb
-glfw==2.9.0
-    # via
-    #   dm-control
-    #   mujoco
-grpcio==1.73.1
-    # via
-    #   grpcio-tools
-    #   lerobot
-grpcio-tools==1.73.1
-    # via lerobot
-gym-aloha==0.1.1
-    # via lerobot
-gym-hil==0.1.10
-    # via lerobot
-gym-pusht==0.1.5
-    # via lerobot
-gym-xarm==0.1.1
-    # via lerobot
-gymnasium==0.29.1
-    # via
-    #   gym-aloha
-    #   gym-hil
-    #   gym-pusht
-    #   gym-xarm
-    #   gymnasium-robotics
-    #   lerobot
-    #   pettingzoo
-gymnasium-robotics==1.2.4
-    # via gym-xarm
-hf-transfer==0.1.9
-    # via huggingface-hub
-hf-xet==1.1.5
-    # via huggingface-hub
-hidapi==0.14.0.post4
-    # via
-    #   gym-hil
-    #   lerobot
-huggingface-hub[cli,hf-transfer]==0.34.3
-    # via
-    #   accelerate
-    #   datasets
-    #   diffusers
-    #   lerobot
-    #   tokenizers
-    #   transformers
-identify==2.6.12
-    # via pre-commit
-idna==3.10
-    # via
-    #   requests
-    #   yarl
-imageio[ffmpeg]==2.37.0
-    # via
-    #   gym-aloha
-    #   gym-hil
-    #   gymnasium-robotics
-    #   lerobot
-    #   scikit-image
-imageio-ffmpeg==0.6.0
-    # via imageio
-importlib-metadata==8.7.0
-    # via diffusers
-iniconfig==2.1.0
-    # via pytest
-inquirerpy==0.3.4
-    # via huggingface-hub
-ipython==8.37.0
-    # via meshcat
-ischedule==1.2.7
-    # via placo
-itsdangerous==2.2.0
-    # via flask
-jedi==0.19.2
-    # via ipython
-jinja2==3.1.6
-    # via
-    #   flask
-    #   gymnasium-robotics
-    #   torch
-jsonlines==4.0.0
-    # via lerobot
-kiwisolver==1.4.8
-    # via matplotlib
-labmaze==1.0.6
-    # via dm-control
-lazy-loader==0.4
-    # via scikit-image
-lxml==6.0.0
-    # via dm-control
-markupsafe==3.0.2
-    # via
-    #   flask
-    #   jinja2
-    #   werkzeug
-matplotlib==3.10.5
-    # via lerobot
-matplotlib-inline==0.1.7
-    # via ipython
-mergedeep==1.3.4
-    # via draccus
-meshcat==0.3.2
-    # via placo
-mock-serial==0.0.1
-    # via lerobot
-mpmath==1.3.0
-    # via sympy
-mujoco==2.3.7
-    # via
-    #   dm-control
-    #   gym-aloha
-    #   gym-hil
-    #   gym-xarm
-    #   gymnasium-robotics
-multidict==6.6.3
-    # via
-    #   aiohttp
-    #   yarl
-multiprocess==0.70.16
-    # via datasets
-mypy-extensions==1.1.0
-    # via typing-inspect
-networkx==3.4.2
-    # via
-    #   scikit-image
-    #   torch
-nodeenv==1.9.1
-    # via pre-commit
-num2words==0.5.14
-    # via lerobot
-numpy==2.2.6
-    # via
-    #   accelerate
-    #   cmeel-boost
-    #   contourpy
-    #   datasets
-    #   diffusers
-    #   dm-control
-    #   dm-env
-    #   dm-tree
-    #   gymnasium
-    #   gymnasium-robotics
-    #   imageio
-    #   labmaze
-    #   matplotlib
-    #   meshcat
-    #   mujoco
-    #   opencv-python
-    #   opencv-python-headless
-    #   pandas
-    #   pettingzoo
-    #   rerun-sdk
-    #   scikit-image
-    #   scipy
-    #   shapely
-    #   tifffile
-    #   torchvision
-    #   transformers
-nvidia-cublas-cu12==12.6.4.1
-    # via
-    #   nvidia-cudnn-cu12
-    #   nvidia-cusolver-cu12
-    #   torch
-nvidia-cuda-cupti-cu12==12.6.80
-    # via torch
-nvidia-cuda-nvrtc-cu12==12.6.77
-    # via torch
-nvidia-cuda-runtime-cu12==12.6.77
-    # via torch
-nvidia-cudnn-cu12==9.5.1.17
-    # via torch
-nvidia-cufft-cu12==11.3.0.4
-    # via torch
-nvidia-cufile-cu12==1.11.1.6
-    # via torch
-nvidia-curand-cu12==10.3.7.77
-    # via torch
-nvidia-cusolver-cu12==11.7.1.2
-    # via torch
-nvidia-cusparse-cu12==12.5.4.2
-    # via
-    #   nvidia-cusolver-cu12
-    #   torch
-nvidia-cusparselt-cu12==0.6.3
-    # via torch
-nvidia-nccl-cu12==2.26.2
-    # via torch
-nvidia-nvjitlink-cu12==12.6.85
-    # via
-    #   nvidia-cufft-cu12
-    #   nvidia-cusolver-cu12
-    #   nvidia-cusparse-cu12
-    #   torch
-nvidia-nvtx-cu12==12.6.77
-    # via torch
-opencv-python==4.12.0.88
-    # via gym-pusht
-opencv-python-headless==4.12.0.88
-    # via lerobot
-orderly-set==5.5.0
-    # via deepdiff
-packaging==25.0
-    # via
-    #   accelerate
-    #   datasets
-    #   huggingface-hub
-    #   lazy-loader
-    #   lerobot
-    #   matplotlib
-    #   pytest
-    #   scikit-image
-    #   transformers
-    #   wandb
-pandas==2.3.1
-    # via
-    #   datasets
-    #   lerobot
-parso==0.8.4
-    # via jedi
-pettingzoo==1.24.3
-    # via gymnasium-robotics
-pexpect==4.9.0
-    # via ipython
-pfzy==0.3.4
-    # via inquirerpy
-pillow==11.3.0
-    # via
-    #   diffusers
-    #   imageio
-    #   matplotlib
-    #   meshcat
-    #   rerun-sdk
-    #   scikit-image
-    #   torchvision
-pin==3.4.0
-    # via placo
-placo==0.9.14
-    # via lerobot
-platformdirs==4.3.8
-    # via
-    #   virtualenv
-    #   wandb
-pluggy==1.6.0
-    # via
-    #   pytest
-    #   pytest-cov
-pre-commit==4.2.0
-    # via lerobot
-prompt-toolkit==3.0.51
-    # via
-    #   inquirerpy
-    #   ipython
-propcache==0.3.2
-    # via
-    #   aiohttp
-    #   yarl
-protobuf==6.31.0
-    # via
-    #   dm-control
-    #   grpcio-tools
-    #   lerobot
-    #   wandb
-psutil==7.0.0
-    # via
-    #   accelerate
-    #   imageio
-ptyprocess==0.7.0
-    # via pexpect
-pure-eval==0.2.3
-    # via stack-data
-pyarrow==21.0.0
-    # via
-    #   datasets
-    #   rerun-sdk
-pycparser==2.22
-    # via cffi
-pydantic==2.11.7
-    # via wandb
-pydantic-core==2.33.2
-    # via pydantic
-pygame==2.6.1
-    # via
-    #   gym-hil
-    #   gym-pusht
-    #   lerobot
-pygments==2.19.2
-    # via
-    #   ipython
-    #   pytest
-pymunk==6.11.1
-    # via
-    #   gym-pusht
-    #   lerobot
-pyngrok==7.2.12
-    # via meshcat
-pynput==1.8.1
-    # via
-    #   gym-hil
-    #   lerobot
-pyopengl==3.1.9
-    # via
-    #   dm-control
-    #   mujoco
-pyparsing==3.2.3
-    # via
-    #   dm-control
-    #   matplotlib
-pyrealsense2==2.56.5.9235
-    # via lerobot
-pyserial==3.5
-    # via
-    #   dynamixel-sdk
-    #   feetech-servo-sdk
-    #   lerobot
-pytest==8.4.1
-    # via
-    #   lerobot
-    #   pytest-cov
-    #   pytest-timeout
-pytest-cov==6.2.1
-    # via lerobot
-pytest-timeout==2.4.0
-    # via lerobot
-python-dateutil==2.9.0.post0
-    # via
-    #   matplotlib
-    #   pandas
-python-xlib==0.33
-    # via pynput
-pytz==2025.2
-    # via pandas
-pyyaml==6.0.2
-    # via
-    #   accelerate
-    #   datasets
-    #   draccus
-    #   huggingface-hub
-    #   pre-commit
-    #   pyngrok
-    #   pyyaml-include
-    #   transformers
-    #   wandb
-pyyaml-include==1.4.1
-    # via draccus
-pyzmq==27.0.0
-    # via
-    #   lerobot
-    #   meshcat
-regex==2025.7.34
-    # via
-    #   diffusers
-    #   transformers
-requests==2.32.4
-    # via
-    #   datasets
-    #   diffusers
-    #   dm-control
-    #   huggingface-hub
-    #   transformers
-    #   wandb
-rerun-sdk==0.22.1
-    # via lerobot
-rhoban-cmeel-jsoncpp==1.9.4.9
-    # via placo
-safetensors==0.5.3
-    # via
-    #   accelerate
-    #   diffusers
-    #   lerobot
-    #   transformers
-scikit-image==0.25.2
-    # via
-    #   gym-pusht
-    #   lerobot
-scipy==1.15.3
-    # via
-    #   dm-control
-    #   scikit-image
-sentry-sdk==2.34.1
-    # via wandb
-shapely==2.1.1
-    # via gym-pusht
-six==1.17.0
-    # via
-    #   pynput
-    #   python-dateutil
-    #   python-xlib
-smmap==5.0.2
-    # via gitdb
-stack-data==0.6.3
-    # via ipython
-sympy==1.14.0
-    # via torch
-termcolor==3.1.0
-    # via lerobot
-tifffile==2025.5.10
-    # via scikit-image
-tokenizers==0.21.4
-    # via transformers
-toml==0.10.2
-    # via draccus
-tomli==2.2.1
-    # via
-    #   cmeel
-    #   coverage
-    #   pytest
-torch==2.7.1
-    # via
-    #   accelerate
-    #   lerobot
-    #   torchvision
-torchcodec==0.5
-    # via lerobot
-torchvision==0.22.1
-    # via lerobot
-tornado==6.5.1
-    # via meshcat
-tqdm==4.67.1
-    # via
-    #   datasets
-    #   dm-control
-    #   huggingface-hub
-    #   transformers
-traitlets==5.14.3
-    # via
-    #   ipython
-    #   matplotlib-inline
-transformers==4.51.3
-    # via lerobot
-triton==3.3.1
-    # via torch
-typing-extensions==4.14.1
-    # via
-    #   aiosignal
-    #   exceptiongroup
-    #   gymnasium
-    #   huggingface-hub
-    #   ipython
-    #   multidict
-    #   pydantic
-    #   pydantic-core
-    #   rerun-sdk
-    #   torch
-    #   typing-inspect
-    #   typing-inspection
-    #   wandb
-typing-inspect==0.9.0
-    # via draccus
-typing-inspection==0.4.1
-    # via pydantic
-tzdata==2025.2
-    # via pandas
-u-msgpack-python==2.8.0
-    # via meshcat
-urllib3==2.5.0
-    # via
-    #   requests
-    #   sentry-sdk
-virtualenv==20.32.0
-    # via pre-commit
-wandb==0.21.0
-    # via lerobot
-wcwidth==0.2.13
-    # via prompt-toolkit
-werkzeug==3.1.3
-    # via flask
-wrapt==1.17.2
-    # via dm-tree
-xxhash==3.5.0
-    # via datasets
-yarl==1.20.1
-    # via aiohttp
-zipp==3.23.0
-    # via importlib-metadata
-
-# The following packages are considered to be unsafe in a requirements file:
-# setuptools

requirements.in

@@ -1,9 +0,0 @@
-# requirements.in
-
-# requirements-macos.txt was generated on macOS and is platform-specific (macOS 15.5 24F74 arm64).
-# Darwin MacBook-Pro.local 24.5.0 Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:43 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T8132 arm64
-
-# requirements-ubuntu.txt was generated on Linux and is platform-specific (Ubuntu 24.04.2 LTS x86_64).
-# Linux mlerobot-linux 6.14.0-27-generic #27~24.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue Jul 22 17:38:49 UTC 2 x86_64 x86_64 x86_64 GNU/Linux
-
--e .[all]

src/lerobot/calibrate.py

@@ -18,7 +18,7 @@ Helper to recalibrate your device (robot or teleoperator).
 Example:
 
 ```shell
-lerobot-calibrate \
+python -m lerobot.calibrate \
     --teleop.type=so100_leader \
     --teleop.port=/dev/tty.usbmodem58760431551 \
     --teleop.id=blue
@@ -82,9 +82,5 @@ def calibrate(cfg: CalibrateConfig):
     device.disconnect()
 
 
-def main():
-    calibrate()
-
-
 if __name__ == "__main__":
-    main()
+    calibrate()

src/lerobot/cameras/opencv/camera_opencv.py

@@ -60,7 +60,7 @@ class OpenCVCamera(Camera):
     or port changes, especially on Linux. Use the provided utility script to find
     available camera indices or paths:
     ```bash
-    lerobot-find-cameras opencv
+    python -m lerobot.find_cameras opencv
     ```
 
     The camera's default settings (FPS, resolution, color mode) are used unless
@@ -165,7 +165,8 @@ class OpenCVCamera(Camera):
             self.videocapture.release()
             self.videocapture = None
             raise ConnectionError(
-                f"Failed to open {self}.Run `lerobot-find-cameras opencv` to find available cameras."
+                f"Failed to open {self}."
+                f"Run `python -m lerobot.find_cameras opencv` to find available cameras."
             )
 
         self._configure_capture_settings()

src/lerobot/cameras/realsense/camera_realsense.py

@@ -51,7 +51,7 @@ class RealSenseCamera(Camera):
 
     Use the provided utility script to find available camera indices and default profiles:
     ```bash
-    lerobot-find-cameras realsense
+    python -m lerobot.find_cameras realsense
     ```
 
     A `RealSenseCamera` instance requires a configuration object specifying the
@@ -176,7 +176,8 @@ class RealSenseCamera(Camera):
             self.rs_profile = None
             self.rs_pipeline = None
             raise ConnectionError(
-                f"Failed to open {self}.Run `lerobot-find-cameras realsense` to find available cameras."
+                f"Failed to open {self}."
+                "Run `python -m lerobot.find_cameras realsense` to find available cameras."
             ) from e
 
         self._configure_capture_settings()

src/lerobot/configs/policies.py

@@ -27,7 +27,6 @@ from huggingface_hub.constants import CONFIG_NAME
 from huggingface_hub.errors import HfHubHTTPError
 
 from lerobot.configs.types import FeatureType, NormalizationMode, PolicyFeature
-from lerobot.constants import ACTION, OBS_STATE
 from lerobot.optim.optimizers import OptimizerConfig
 from lerobot.optim.schedulers import LRSchedulerConfig
 from lerobot.utils.hub import HubMixin
@@ -120,8 +119,8 @@ class PreTrainedConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC):
 
     @property
     def robot_state_feature(self) -> PolicyFeature | None:
-        for ft_name, ft in self.input_features.items():
-            if ft.type is FeatureType.STATE and ft_name == OBS_STATE:
+        for _, ft in self.input_features.items():
+            if ft.type is FeatureType.STATE:
                 return ft
         return None
 
@@ -138,8 +137,8 @@ class PreTrainedConfig(draccus.ChoiceRegistry, HubMixin, abc.ABC):
 
     @property
     def action_feature(self) -> PolicyFeature | None:
-        for ft_name, ft in self.output_features.items():
-            if ft.type is FeatureType.ACTION and ft_name == ACTION:
+        for _, ft in self.output_features.items():
+            if ft.type is FeatureType.ACTION:
                 return ft
         return None
 

src/lerobot/datasets/lerobot_dataset.py

@@ -825,8 +825,6 @@ class LeRobotDataset(torch.utils.data.Dataset):
         """
         if not episode_data:
             episode_buffer = self.episode_buffer
-        else:
-            episode_buffer = episode_data
 
         validate_episode_buffer(episode_buffer, self.meta.total_episodes, self.features)
 

src/lerobot/envs/configs.py

@@ -161,35 +161,74 @@ class XarmEnv(EnvConfig):
 
 
 @dataclass
-class VideoRecordConfig:
-    """Configuration for video recording in ManiSkill environments."""
-
-    enabled: bool = False
-    record_dir: str = "videos"
-    trajectory_name: str = "trajectory"
+class ImagePreprocessingConfig:
+    crop_params_dict: dict[str, tuple[int, int, int, int]] | None = None
+    resize_size: tuple[int, int] | None = None
 
 
 @dataclass
-class EnvTransformConfig:
-    """Configuration for environment wrappers."""
+class RewardClassifierConfig:
+    """Configuration for reward classification."""
+
+    pretrained_path: str | None = None
+    success_threshold: float = 0.5
+    success_reward: float = 1.0
+
+
+@dataclass
+class InverseKinematicsConfig:
+    """Configuration for inverse kinematics processing."""
+
+    urdf_path: str | None = None
+    target_frame_name: str | None = None
+    end_effector_bounds: dict[str, list[float]] | None = None
+    end_effector_step_sizes: dict[str, float] | None = None
+    max_gripper_pos: float | None = None
+
+
+@dataclass
+class ObservationConfig:
+    """Configuration for observation processing."""
 
-    # ee_action_space_params: EEActionSpaceConfig = field(default_factory=EEActionSpaceConfig)
-    control_mode: str = "gamepad"
-    display_cameras: bool = False
     add_joint_velocity_to_observation: bool = False
     add_current_to_observation: bool = False
     add_ee_pose_to_observation: bool = False
-    crop_params_dict: dict[str, tuple[int, int, int, int]] | None = None
-    resize_size: tuple[int, int] | None = None
-    control_time_s: float = 20.0
-    fixed_reset_joint_positions: Any | None = None
-    reset_time_s: float = 5.0
+    display_cameras: bool = False
+
+
+@dataclass
+class GripperConfig:
+    """Configuration for gripper control and penalties."""
+
     use_gripper: bool = True
-    gripper_quantization_threshold: float | None = 0.8
     gripper_penalty: float = 0.0
     gripper_penalty_in_reward: bool = False
 
 
+@dataclass
+class ResetConfig:
+    """Configuration for environment reset behavior."""
+
+    fixed_reset_joint_positions: Any | None = None
+    reset_time_s: float = 5.0
+    control_time_s: float = 20.0
+    terminate_on_success: bool = True
+    number_of_steps_after_success: int = 0
+
+
+@dataclass
+class HILSerlProcessorConfig:
+    """Configuration for environment processing pipeline."""
+
+    control_mode: str = "gamepad"
+    observation: ObservationConfig = field(default_factory=ObservationConfig)
+    image_preprocessing: ImagePreprocessingConfig = field(default_factory=ImagePreprocessingConfig)
+    gripper: GripperConfig = field(default_factory=GripperConfig)
+    reset: ResetConfig = field(default_factory=ResetConfig)
+    inverse_kinematics: InverseKinematicsConfig = field(default_factory=InverseKinematicsConfig)
+    reward_classifier: RewardClassifierConfig = field(default_factory=RewardClassifierConfig)
+
+
 @EnvConfig.register_subclass(name="gym_manipulator")
 @dataclass
 class HILSerlRobotEnvConfig(EnvConfig):
@@ -197,77 +236,11 @@ class HILSerlRobotEnvConfig(EnvConfig):
 
     robot: RobotConfig | None = None
     teleop: TeleoperatorConfig | None = None
-    wrapper: EnvTransformConfig | None = None
-    fps: int = 10
+    processor: HILSerlProcessorConfig = field(default_factory=HILSerlProcessorConfig)
+
     name: str = "real_robot"
-    mode: str | None = None  # Either "record", "replay", None
-    repo_id: str | None = None
-    dataset_root: str | None = None
-    task: str | None = ""
-    num_episodes: int = 10  # only for record mode
-    episode: int = 0
     device: str = "cuda"
-    push_to_hub: bool = True
-    pretrained_policy_name_or_path: str | None = None
-    reward_classifier_pretrained_path: str | None = None
-    # For the reward classifier, to record more positive examples after a success
-    number_of_steps_after_success: int = 0
 
     @property
     def gym_kwargs(self) -> dict:
         return {}
-
-
-@EnvConfig.register_subclass("hil")
-@dataclass
-class HILEnvConfig(EnvConfig):
-    """Configuration for the HIL environment."""
-
-    name: str = "PandaPickCube"
-    task: str | None = "PandaPickCubeKeyboard-v0"
-    use_viewer: bool = True
-    gripper_penalty: float = 0.0
-    use_gamepad: bool = True
-    state_dim: int = 18
-    action_dim: int = 4
-    fps: int = 100
-    episode_length: int = 100
-    video_record: VideoRecordConfig = field(default_factory=VideoRecordConfig)
-    features: dict[str, PolicyFeature] = field(
-        default_factory=lambda: {
-            "action": PolicyFeature(type=FeatureType.ACTION, shape=(4,)),
-            "observation.image": PolicyFeature(type=FeatureType.VISUAL, shape=(3, 128, 128)),
-            "observation.state": PolicyFeature(type=FeatureType.STATE, shape=(18,)),
-        }
-    )
-    features_map: dict[str, str] = field(
-        default_factory=lambda: {
-            "action": ACTION,
-            "observation.image": OBS_IMAGE,
-            "observation.state": OBS_STATE,
-        }
-    )
-    ################# args from hilserlrobotenv
-    reward_classifier_pretrained_path: str | None = None
-    robot_config: RobotConfig | None = None
-    teleop_config: TeleoperatorConfig | None = None
-    wrapper: EnvTransformConfig | None = None
-    mode: str | None = None  # Either "record", "replay", None
-    repo_id: str | None = None
-    dataset_root: str | None = None
-    num_episodes: int = 10  # only for record mode
-    episode: int = 0
-    device: str = "cuda"
-    push_to_hub: bool = True
-    pretrained_policy_name_or_path: str | None = None
-    # For the reward classifier, to record more positive examples after a success
-    number_of_steps_after_success: int = 0
-    ############################
-
-    @property
-    def gym_kwargs(self) -> dict:
-        return {
-            "use_viewer": self.use_viewer,
-            "use_gamepad": self.use_gamepad,
-            "gripper_penalty": self.gripper_penalty,
-        }

src/lerobot/envs/utils.py

@@ -16,10 +16,8 @@
 import warnings
 from typing import Any
 
-import einops
 import gymnasium as gym
 import numpy as np
-import torch
 from torch import Tensor
 
 from lerobot.configs.types import FeatureType, PolicyFeature
@@ -28,62 +26,40 @@ from lerobot.utils.utils import get_channel_first_image_shape
 
 
 def preprocess_observation(observations: dict[str, np.ndarray]) -> dict[str, Tensor]:
-    # TODO(aliberts, rcadene): refactor this to use features from the environment (no hardcoding)
     """Convert environment observation to LeRobot format observation.
+
+    This function uses the new pipeline system internally but maintains
+    backward compatibility with the original interface.
+
     Args:
         observation: Dictionary of observation batches from a Gym vector environment.
     Returns:
         Dictionary of observation batches with keys renamed to LeRobot format and values as tensors.
     """
-    # map to expected inputs for the policy
-    return_observations = {}
-    if "pixels" in observations:
-        if isinstance(observations["pixels"], dict):
-            imgs = {f"observation.images.{key}": img for key, img in observations["pixels"].items()}
-        else:
-            imgs = {"observation.image": observations["pixels"]}
+    from lerobot.processor import RobotProcessor, TransitionKey, VanillaObservationProcessor
 
-        for imgkey, img in imgs.items():
-            # TODO(aliberts, rcadene): use transforms.ToTensor()?
-            img = torch.from_numpy(img)
+    # Create processor with observation processor
+    processor = RobotProcessor([VanillaObservationProcessor()])
 
-            # When preprocessing observations in a non-vectorized environment, we need to add a batch dimension.
-            # This is the case for human-in-the-loop RL where there is only one environment.
-            if img.ndim == 3:
-                img = img.unsqueeze(0)
-            # sanity check that images are channel last
-            _, h, w, c = img.shape
-            assert c < h and c < w, f"expect channel last images, but instead got {img.shape=}"
+    # Create transition dictionary and process
+    transition = {
+        TransitionKey.OBSERVATION: observations,
+        TransitionKey.ACTION: None,
+        TransitionKey.REWARD: None,
+        TransitionKey.DONE: None,
+        TransitionKey.TRUNCATED: None,
+        TransitionKey.INFO: None,
+        TransitionKey.COMPLEMENTARY_DATA: None,
+    }
+    result = processor(transition)
 
-            # sanity check that images are uint8
-            assert img.dtype == torch.uint8, f"expect torch.uint8, but instead {img.dtype=}"
-
-            # convert to channel first of type float32 in range [0,1]
-            img = einops.rearrange(img, "b h w c -> b c h w").contiguous()
-            img = img.type(torch.float32)
-            img /= 255
-
-            return_observations[imgkey] = img
-
-    if "environment_state" in observations:
-        env_state = torch.from_numpy(observations["environment_state"]).float()
-        if env_state.dim() == 1:
-            env_state = env_state.unsqueeze(0)
-
-        return_observations["observation.environment_state"] = env_state
-
-    # TODO(rcadene): enable pixels only baseline with `obs_type="pixels"` in environment by removing
-    agent_pos = torch.from_numpy(observations["agent_pos"]).float()
-    if agent_pos.dim() == 1:
-        agent_pos = agent_pos.unsqueeze(0)
-    return_observations["observation.state"] = agent_pos
-
-    return return_observations
+    # Extract and return the processed observation
+    return result[TransitionKey.OBSERVATION]
 
 
 def env_to_policy_features(env_cfg: EnvConfig) -> dict[str, PolicyFeature]:
     # TODO(aliberts, rcadene): remove this hardcoding of keys and just use the nested keys as is
-    # (need to also refactor preprocess_observation and externalize normalization from policies)
+    # (need to externalize normalization from policies)
     policy_features = {}
     for key, ft in env_cfg.features.items():
         if ft.type is FeatureType.VISUAL:

src/lerobot/find_cameras.py

@@ -20,7 +20,7 @@ Helper to find the camera devices available in your system.
 Example:
 
 ```shell
-lerobot-find-cameras
+python -m lerobot.find_cameras
 ```
 """
 
@@ -286,7 +286,7 @@ def save_images_from_all_cameras(
             print(f"Image capture finished. Images saved to {output_dir}")
 
 
-def main():
+if __name__ == "__main__":
     parser = argparse.ArgumentParser(
         description="Unified camera utility script for listing cameras and capturing images."
     )
@@ -313,7 +313,3 @@ def main():
     )
     args = parser.parse_args()
     save_images_from_all_cameras(**vars(args))
-
-
-if __name__ == "__main__":
-    main()

src/lerobot/find_port.py

@@ -18,7 +18,7 @@ Helper to find the USB port associated with your MotorsBus.
 Example:
 
 ```shell
-lerobot-find-port
+python -m lerobot.find_port
 ```
 """
 
@@ -61,9 +61,5 @@ def find_port():
         raise OSError(f"Could not detect the port. More than one port was found ({ports_diff}).")
 
 
-def main():
-    find_port()
-
-
 if __name__ == "__main__":
-    main()
+    find_port()

src/lerobot/motors/dynamixel/tables.py

@@ -107,8 +107,6 @@ X_SERIES_ENCODINGS_TABLE = {
     "Goal_PWM": X_SERIES_CONTROL_TABLE["Goal_PWM"][1],
     "Goal_Current": X_SERIES_CONTROL_TABLE["Goal_Current"][1],
     "Goal_Velocity": X_SERIES_CONTROL_TABLE["Goal_Velocity"][1],
-    "Goal_Position": X_SERIES_CONTROL_TABLE["Goal_Position"][1],
-    "Present_Position": X_SERIES_CONTROL_TABLE["Present_Position"][1],
     "Present_PWM": X_SERIES_CONTROL_TABLE["Present_PWM"][1],
     "Present_Current": X_SERIES_CONTROL_TABLE["Present_Current"][1],
     "Present_Velocity": X_SERIES_CONTROL_TABLE["Present_Velocity"][1],

src/lerobot/motors/motors_bus.py

@@ -222,7 +222,7 @@ class MotorsBus(abc.ABC):
     A MotorsBus subclass instance requires a port (e.g. `FeetechMotorsBus(port="/dev/tty.usbmodem575E0031751"`)).
     To find the port, you can run our utility script:
     ```bash
-    lerobot-find-port.py
+    python -m lerobot.find_port.py
     >>> Finding all available ports for the MotorsBus.
     >>> ["/dev/tty.usbmodem575E0032081", "/dev/tty.usbmodem575E0031751"]
     >>> Remove the usb cable from your MotorsBus and press Enter when done.
@@ -446,7 +446,7 @@ class MotorsBus(abc.ABC):
         except (FileNotFoundError, OSError, serial.SerialException) as e:
             raise ConnectionError(
                 f"\nCould not connect on port '{self.port}'. Make sure you are using the correct port."
-                "\nTry running `lerobot-find-port`\n"
+                "\nTry running `python -m lerobot.find_port`\n"
             ) from e
 
     @abc.abstractmethod

src/lerobot/policies/act/README.md

@@ -1 +0,0 @@
-../../../../docs/source/policy_act_README.md

src/lerobot/policies/diffusion/README.md

@@ -1 +0,0 @@
-../../../../docs/source/policy_diffusion_README.md

src/lerobot/policies/pi0/modeling_pi0.py

@@ -30,7 +30,7 @@ pip install -e ".[pi0]"
 
 Example of finetuning the pi0 pretrained model (`pi0_base` in `openpi`):
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.path=lerobot/pi0 \
 --dataset.repo_id=danaaubakirova/koch_test
 ```
@@ -38,7 +38,7 @@ lerobot-train \
 Example of finetuning the pi0 neural network with PaliGemma and expert Gemma
 pretrained with VLM default parameters before pi0 finetuning:
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.type=pi0 \
 --dataset.repo_id=danaaubakirova/koch_test
 ```

src/lerobot/policies/pi0fast/modeling_pi0fast.py

@@ -25,14 +25,14 @@ Disclaimer: It is not expected to perform as well as the original implementation
 
 Example of finetuning the pi0+FAST pretrained model (`pi0_fast_base` in `openpi`):
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.path=lerobot/pi0fast_base \
 --dataset.repo_id=danaaubakirova/koch_test
 ```
 
 Example of training the pi0+FAST neural network with from scratch:
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.type=pi0fast \
 --dataset.repo_id=danaaubakirova/koch_test
 ```

src/lerobot/policies/smolvla/README.md

@@ -1 +0,0 @@
-../../../../docs/source/policy_smolvla_README.md

src/lerobot/policies/smolvla/modeling_smolvla.py

@@ -28,7 +28,7 @@ pip install -e ".[smolvla]"
 
 Example of finetuning the smolvla pretrained model (`smolvla_base`):
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.path=lerobot/smolvla_base \
 --dataset.repo_id=danaaubakirova/svla_so100_task1_v3 \
 --batch_size=64 \
@@ -38,7 +38,7 @@ lerobot-train \
 Example of finetuning a smolVLA. SmolVLA is composed of a pretrained VLM,
 and an action expert.
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
 --policy.type=smolvla \
 --dataset.repo_id=danaaubakirova/svla_so100_task1_v3 \
 --batch_size=64 \

src/lerobot/policies/tdmpc/README.md

@@ -1 +0,0 @@
-../../../../docs/source/policy_tdmpc_README.md

src/lerobot/policies/vqbet/README.md

@@ -1 +0,0 @@
-../../../../docs/source/policy_vqbet_README.md

src/lerobot/processor/__init__.py

@@ -15,8 +15,18 @@
 # limitations under the License.
 
 from .device_processor import DeviceProcessor
+from .hil_processor import (
+    GripperPenaltyProcessor,
+    ImageCropResizeProcessor,
+    InterventionActionProcessor,
+    TimeLimitProcessor,
+)
 from .normalize_processor import NormalizerProcessor, UnnormalizerProcessor
-from .observation_processor import VanillaObservationProcessor
+from .observation_processor import (
+    ImageProcessor,
+    StateProcessor,
+    VanillaObservationProcessor,
+)
 from .pipeline import (
     ActionProcessor,
     DoneProcessor,
@@ -32,14 +42,26 @@ from .pipeline import (
     TruncatedProcessor,
 )
 from .rename_processor import RenameProcessor
+from .robot_processor import (
+    InverseKinematicsProcessor,
+    JointVelocityProcessor,
+    MotorCurrentProcessor,
+)
 
 __all__ = [
     "ActionProcessor",
     "DeviceProcessor",
     "DoneProcessor",
     "EnvTransition",
+    "GripperPenaltyProcessor",
     "IdentityProcessor",
+    "ImageCropResizeProcessor",
+    "ImageProcessor",
     "InfoProcessor",
+    "InterventionActionProcessor",
+    "InverseKinematicsProcessor",
+    "JointVelocityProcessor",
+    "MotorCurrentProcessor",
     "NormalizerProcessor",
     "UnnormalizerProcessor",
     "ObservationProcessor",
@@ -48,6 +70,8 @@ __all__ = [
     "RenameProcessor",
     "RewardProcessor",
     "RobotProcessor",
+    "StateProcessor",
+    "TimeLimitProcessor",
     "TransitionKey",
     "TruncatedProcessor",
     "VanillaObservationProcessor",

src/lerobot/processor/device_processor.py

@@ -20,7 +20,6 @@ import torch
 
 from lerobot.configs.types import PolicyFeature
 from lerobot.processor.pipeline import EnvTransition, TransitionKey
-from lerobot.utils.utils import get_safe_torch_device
 
 
 @dataclass
@@ -31,11 +30,10 @@ class DeviceProcessor:
     specified device (CPU or GPU) before they are returned.
     """
 
-    device: torch.device = "cpu"
+    device: str = "cpu"
 
     def __post_init__(self):
-        self.device = get_safe_torch_device(self.device)
-        self.non_blocking = "cuda" in str(self.device)
+        self.non_blocking = "cuda" in self.device
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         # Create a copy of the transition

src/lerobot/processor/hil_processor.py

@@ -0,0 +1,331 @@
+import time
+from dataclasses import dataclass
+from typing import Any
+
+import torch
+import torchvision.transforms.functional as F  # noqa: N812
+
+from lerobot.configs.types import PolicyFeature
+from lerobot.processor.pipeline import EnvTransition, ProcessorStepRegistry, TransitionKey
+
+
+@dataclass
+@ProcessorStepRegistry.register("image_crop_resize_processor")
+class ImageCropResizeProcessor:
+    """Crop and resize image observations."""
+
+    crop_params_dict: dict[str, tuple[int, int, int, int]]
+    resize_size: tuple[int, int] = (128, 128)
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+        if observation is None:
+            return transition
+
+        if self.resize_size is None and not self.crop_params_dict:
+            return transition
+
+        new_observation = dict(observation)
+
+        # Process all image keys in the observation
+        for key in observation:
+            if "image" not in key:
+                continue
+
+            image = observation[key]
+            device = image.device
+            if device.type == "mps":
+                image = image.cpu()
+            # Crop if crop params are provided for this key
+            if key in self.crop_params_dict:
+                crop_params = self.crop_params_dict[key]
+                image = F.crop(image, *crop_params)
+            # Always resize
+            image = F.resize(image, self.resize_size)
+            image = image.clamp(0.0, 1.0)
+            new_observation[key] = image.to(device)
+
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = new_observation
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "crop_params_dict": self.crop_params_dict,
+            "resize_size": self.resize_size,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        pass
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("time_limit_processor")
+class TimeLimitProcessor:
+    """Track episode time and enforce time limits."""
+
+    max_episode_steps: int
+    current_step: int = 0
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        truncated = transition.get(TransitionKey.TRUNCATED)
+        if truncated is None:
+            return transition
+
+        self.current_step += 1
+        if self.current_step >= self.max_episode_steps:
+            truncated = True
+        new_transition = transition.copy()
+        new_transition[TransitionKey.TRUNCATED] = truncated
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "max_episode_steps": self.max_episode_steps,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        self.current_step = 0
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("gripper_penalty_processor")
+class GripperPenaltyProcessor:
+    penalty: float = -0.01
+    max_gripper_pos: float = 30.0
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        """Calculate gripper penalty and add to complementary data."""
+        action = transition.get(TransitionKey.ACTION)
+        complementary_data = transition.get(TransitionKey.COMPLEMENTARY_DATA)
+
+        if complementary_data is None or action is None:
+            return transition
+
+        current_gripper_pos = complementary_data.get("raw_joint_positions", None)[-1]
+        if current_gripper_pos is None:
+            return transition
+
+        gripper_action = action[-1].item()
+        gripper_action_normalized = gripper_action / self.max_gripper_pos
+
+        # Normalize gripper state and action
+        gripper_state_normalized = current_gripper_pos / self.max_gripper_pos
+        gripper_action_normalized = gripper_action - 1.0
+
+        # Calculate penalty boolean as in original
+        gripper_penalty_bool = (gripper_state_normalized < 0.5 and gripper_action_normalized > 0.5) or (
+            gripper_state_normalized > 0.75 and gripper_action_normalized < 0.5
+        )
+
+        gripper_penalty = self.penalty * int(gripper_penalty_bool)
+
+        # Add penalty information to complementary data
+        complementary_data = transition.get(TransitionKey.COMPLEMENTARY_DATA, {})
+
+        # Create new complementary data with penalty info
+        new_complementary_data = dict(complementary_data)
+        new_complementary_data["discrete_penalty"] = gripper_penalty
+
+        # Create new transition with updated complementary data
+        new_transition = transition.copy()
+        new_transition[TransitionKey.COMPLEMENTARY_DATA] = new_complementary_data
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "penalty": self.penalty,
+            "max_gripper_pos": self.max_gripper_pos,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        """Reset the processor state."""
+        self.last_gripper_state = None
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("intervention_action_processor")
+class InterventionActionProcessor:
+    """Handle action intervention based on signals in the transition.
+
+    This processor checks for intervention signals in the transition's complementary data
+    and overrides agent actions when intervention is active.
+    """
+
+    use_gripper: bool = False
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        action = transition.get(TransitionKey.ACTION)
+        if action is None:
+            return transition
+
+        # Get intervention signals from complementary data
+        complementary_data = transition.get(TransitionKey.COMPLEMENTARY_DATA, {})
+        teleop_action = complementary_data.get("teleop_action", {})
+        is_intervention = complementary_data.get("is_intervention", False)
+        terminate_episode = complementary_data.get("terminate_episode", False)
+        success = complementary_data.get("success", False)
+        rerecord_episode = complementary_data.get("rerecord_episode", False)
+
+        new_transition = transition.copy()
+
+        # Override action if intervention is active
+        if is_intervention and teleop_action:
+            # Convert teleop_action dict to tensor format
+            action_list = [
+                teleop_action.get("delta_x", 0.0),
+                teleop_action.get("delta_y", 0.0),
+                teleop_action.get("delta_z", 0.0),
+            ]
+            if self.use_gripper:
+                action_list.append(teleop_action.get("gripper", 1.0))
+
+            teleop_action_tensor = torch.tensor(action_list, dtype=action.dtype, device=action.device)
+            new_transition[TransitionKey.ACTION] = teleop_action_tensor
+
+        # Handle episode termination
+        new_transition[TransitionKey.DONE] = bool(terminate_episode)
+        new_transition[TransitionKey.REWARD] = float(success)
+
+        # Update info with intervention metadata
+        info = new_transition.get(TransitionKey.INFO, {})
+        info["is_intervention"] = is_intervention
+        info["rerecord_episode"] = rerecord_episode
+        info["next.success"] = success if terminate_episode else info.get("next.success", False)
+        new_transition[TransitionKey.INFO] = info
+        new_transition[TransitionKey.COMPLEMENTARY_DATA]["teleop_action"] = new_transition[
+            TransitionKey.ACTION
+        ]
+
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "use_gripper": self.use_gripper,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        pass
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("reward_classifier_processor")
+class RewardClassifierProcessor:
+    """Apply reward classification to image observations.
+
+    This processor runs a trained reward classifier on image observations
+    to predict rewards and success states, potentially terminating episodes
+    when success is achieved.
+    """
+
+    pretrained_path: str = None
+    device: str = "cpu"
+    success_threshold: float = 0.5
+    success_reward: float = 1.0
+    terminate_on_success: bool = True
+
+    reward_classifier: Any = None
+
+    def __post_init__(self):
+        """Initialize the reward classifier after dataclass initialization."""
+        if self.pretrained_path is not None:
+            from lerobot.policies.sac.reward_model.modeling_classifier import Classifier
+
+            self.reward_classifier = Classifier.from_pretrained(self.pretrained_path)
+            self.reward_classifier.to(self.device)
+            self.reward_classifier.eval()
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+        if observation is None or self.reward_classifier is None:
+            return transition
+
+        # Extract images from observation
+        images = {key: value for key, value in observation.items() if "image" in key}
+
+        if not images:
+            return transition
+
+        # Run reward classifier
+        start_time = time.perf_counter()
+        with torch.inference_mode():
+            success = self.reward_classifier.predict_reward(images, threshold=self.success_threshold)
+
+        classifier_frequency = 1 / (time.perf_counter() - start_time)
+
+        # Calculate reward and termination
+        reward = transition.get(TransitionKey.REWARD, 0.0)
+        terminated = transition.get(TransitionKey.DONE, False)
+
+        if success == 1.0:
+            reward = self.success_reward
+            if self.terminate_on_success:
+                terminated = True
+
+        # Update transition
+        new_transition = transition.copy()
+        new_transition[TransitionKey.REWARD] = reward
+        new_transition[TransitionKey.DONE] = terminated
+
+        # Update info with classifier frequency
+        info = new_transition.get(TransitionKey.INFO, {})
+        info["reward_classifier_frequency"] = classifier_frequency
+        new_transition[TransitionKey.INFO] = info
+
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "device": self.device,
+            "success_threshold": self.success_threshold,
+            "success_reward": self.success_reward,
+            "terminate_on_success": self.terminate_on_success,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        pass
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features

src/lerobot/processor/normalize_processor.py

@@ -220,6 +220,7 @@ class UnnormalizerProcessor:
     features: dict[str, PolicyFeature]
     norm_map: dict[FeatureType, NormalizationMode]
     stats: dict[str, dict[str, Any]] | None = None
+    eps: float = 1e-8
 
     _tensor_stats: dict[str, dict[str, Tensor]] = field(default_factory=dict, init=False, repr=False)
 
@@ -229,8 +230,10 @@ class UnnormalizerProcessor:
         dataset: LeRobotDataset,
         features: dict[str, PolicyFeature],
         norm_map: dict[FeatureType, NormalizationMode],
+        *,
+        eps: float = 1e-8,
     ) -> UnnormalizerProcessor:
-        return cls(features=features, norm_map=norm_map, stats=dataset.meta.stats)
+        return cls(features=features, norm_map=norm_map, stats=dataset.meta.stats, eps=eps)
 
     def __post_init__(self):
         # Handle deserialization from JSON config
@@ -305,6 +308,7 @@ class UnnormalizerProcessor:
 
     def get_config(self) -> dict[str, Any]:
         return {
+            "eps": self.eps,
             "features": {
                 key: {"type": ft.type.value, "shape": ft.shape} for key, ft in self.features.items()
             },

src/lerobot/processor/observation_processor.py

@@ -13,7 +13,8 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from dataclasses import dataclass
+from dataclasses import dataclass, field
+from typing import Any
 
 import einops
 import numpy as np
@@ -22,28 +23,53 @@ from torch import Tensor
 
 from lerobot.configs.types import PolicyFeature
 from lerobot.constants import OBS_ENV_STATE, OBS_IMAGE, OBS_IMAGES, OBS_STATE
-from lerobot.processor.pipeline import ObservationProcessor, ProcessorStepRegistry
+from lerobot.processor.pipeline import EnvTransition, ProcessorStepRegistry, TransitionKey
 
 
 @dataclass
-@ProcessorStepRegistry.register(name="observation_processor")
-class VanillaObservationProcessor(ObservationProcessor):
-    """
-    Processes environment observations into the LeRobot format by handling both images and states.
+class ImageProcessor:
+    """Process image observations from environment format to policy format.
 
-    Image processing:
-        - Converts channel-last (H, W, C) images to channel-first (C, H, W)
-        - Normalizes uint8 images ([0, 255]) to float32 ([0, 1])
-        - Adds a batch dimension if missing
-        - Supports single images and image dictionaries
-
-    State processing:
-        - Maps 'environment_state' to observation.environment_state
-        - Maps 'agent_pos' to observation.state
-        - Converts numpy arrays to tensors
-        - Adds a batch dimension if missing
+    Converts images from:
+    - Channel-last (H, W, C) to channel-first (C, H, W)
+    - uint8 [0, 255] to float32 [0, 1]
+    - Adds batch dimension if needed
+    - Handles both single images and dictionaries of images
     """
 
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+
+        if observation is None:
+            return transition
+
+        processed_obs = {}
+
+        # Copy all observations first
+        for key, value in observation.items():
+            processed_obs[key] = value
+
+        # Handle pixels key if present
+        pixels = observation.get("pixels")
+        if pixels is not None:
+            # Remove pixels from processed_obs since we'll replace it with processed images
+            processed_obs.pop("pixels", None)
+            # Determine image mapping
+            if isinstance(pixels, dict):
+                imgs = {f"{OBS_IMAGES}.{key}": img for key, img in pixels.items()}
+            else:
+                imgs = {OBS_IMAGE: pixels}
+
+            # Process each image
+            for imgkey, img in imgs.items():
+                processed_img = self._process_single_image(img)
+                processed_obs[imgkey] = processed_img
+
+        # Return new transition with processed observation
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = processed_obs
+        return new_transition
+
     def _process_single_image(self, img: np.ndarray) -> Tensor:
         """Process a single image array."""
         # Convert to tensor
@@ -69,89 +95,173 @@ class VanillaObservationProcessor(ObservationProcessor):
 
         return img_tensor
 
-    def _process_observation(self, observation):
-        """
-        Processes both image and state observations.
+    def get_config(self) -> dict[str, Any]:
+        """Return configuration for serialization."""
+        return {}
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        """Return state dictionary (empty for this processor)."""
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        """Load state dictionary (no-op for this processor)."""
+        pass
+
+    def reset(self) -> None:
+        """Reset processor state (no-op for this processor)."""
+        pass
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        """Transforms:
+        pixels -> OBS_IMAGE,
+        observation.pixels -> OBS_IMAGE,
+        pixels.<cam> -> OBS_IMAGES.<cam>,
+        observation.pixels.<cam> -> OBS_IMAGES.<cam>
         """
+        if "pixels" in features:
+            features[OBS_IMAGE] = features.pop("pixels")
+        if "observation.pixels" in features:
+            features[OBS_IMAGE] = features.pop("observation.pixels")
 
-        processed_obs = observation.copy()
+        prefixes = ("pixels.", "observation.pixels.")
+        for key in list(features.keys()):
+            for p in prefixes:
+                if key.startswith(p):
+                    suffix = key[len(p) :]
+                    features[f"{OBS_IMAGES}.{suffix}"] = features.pop(key)
+                    break
+        return features
 
-        if "pixels" in processed_obs:
-            pixels = processed_obs.pop("pixels")
 
-            if isinstance(pixels, dict):
-                imgs = {f"{OBS_IMAGES}.{key}": img for key, img in pixels.items()}
-            else:
-                imgs = {OBS_IMAGE: pixels}
+@dataclass
+class StateProcessor:
+    """Process state observations from environment format to policy format.
 
-            for imgkey, img in imgs.items():
-                processed_obs[imgkey] = self._process_single_image(img)
+    Handles:
+    - environment_state -> observation.environment_state
+    - agent_pos -> observation.state
+    - Converts numpy arrays to tensors
+    - Adds batch dimension if needed
+    """
 
-        if "environment_state" in processed_obs:
-            env_state_np = processed_obs.pop("environment_state")
-            env_state = torch.from_numpy(env_state_np).float()
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+
+        if observation is None:
+            return transition
+
+        processed_obs = dict(observation)  # Copy existing observations
+
+        # Process environment_state
+        if "environment_state" in observation:
+            env_state = torch.from_numpy(observation["environment_state"]).float()
             if env_state.dim() == 1:
                 env_state = env_state.unsqueeze(0)
             processed_obs[OBS_ENV_STATE] = env_state
+            # Remove original key
+            del processed_obs["environment_state"]
 
-        if "agent_pos" in processed_obs:
-            agent_pos_np = processed_obs.pop("agent_pos")
-            agent_pos = torch.from_numpy(agent_pos_np).float()
+        # Process agent_pos
+        if "agent_pos" in observation:
+            agent_pos = torch.from_numpy(observation["agent_pos"]).float()
             if agent_pos.dim() == 1:
                 agent_pos = agent_pos.unsqueeze(0)
             processed_obs[OBS_STATE] = agent_pos
+            # Remove original key
+            del processed_obs["agent_pos"]
 
-        return processed_obs
+        # Return new transition with processed observation
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = processed_obs
+        return new_transition
 
-    def observation(self, observation):
-        return self._process_observation(observation)
+    def get_config(self) -> dict[str, Any]:
+        """Return configuration for serialization."""
+        return {}
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        """Return state dictionary (empty for this processor)."""
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        """Load state dictionary (no-op for this processor)."""
+        pass
+
+    def reset(self) -> None:
+        """Reset processor state (no-op for this processor)."""
+        pass
 
     def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        """Transforms feature keys to a standardized contract.
-
-        This method handles several renaming patterns:
-        - Exact matches (e.g., 'pixels' -> 'OBS_IMAGE').
-        - Prefixed exact matches (e.g., 'observation.pixels' -> 'OBS_IMAGE').
-        - Prefix matches (e.g., 'pixels.cam1' -> 'OBS_IMAGES.cam1').
-        - Prefixed prefix matches (e.g., 'observation.pixels.cam1' -> 'OBS_IMAGES.cam1').
-        - environment_state -> OBS_ENV_STATE,
-        - agent_pos -> OBS_STATE,
-        - observation.environment_state -> OBS_ENV_STATE,
-        - observation.agent_pos -> OBS_STATE
+        """Transforms:
+        environment_state -> OBS_ENV_STATE,
+        agent_pos -> OBS_STATE,
+        observation.environment_state -> OBS_ENV_STATE,
+        observation.agent_pos -> OBS_STATE
         """
-        exact_pairs = {
-            "pixels": OBS_IMAGE,
-            "environment_state": OBS_ENV_STATE,
-            "agent_pos": OBS_STATE,
-        }
-
-        prefix_pairs = {
-            "pixels.": f"{OBS_IMAGES}.",
-        }
-
-        for key in list(features.keys()):
-            matched_prefix = False
-            for old_prefix, new_prefix in prefix_pairs.items():
-                prefixed_old = f"observation.{old_prefix}"
-                if key.startswith(prefixed_old):
-                    suffix = key[len(prefixed_old) :]
-                    features[f"{new_prefix}{suffix}"] = features.pop(key)
-                    matched_prefix = True
-                    break
-
-                if key.startswith(old_prefix):
-                    suffix = key[len(old_prefix) :]
-                    features[f"{new_prefix}{suffix}"] = features.pop(key)
-                    matched_prefix = True
-                    break
-
-            if matched_prefix:
-                continue
-
-            for old, new in exact_pairs.items():
-                if key == old or key == f"observation.{old}":
-                    if key in features:
-                        features[new] = features.pop(key)
-                        break
-
+        pairs = (
+            ("environment_state", OBS_ENV_STATE),
+            ("agent_pos", OBS_STATE),
+        )
+        for old, new in pairs:
+            if old in features:
+                features[new] = features.pop(old)
+            prefixed = f"observation.{old}"
+            if prefixed in features:
+                features[new] = features.pop(prefixed)
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register(name="observation_processor")
+class VanillaObservationProcessor:
+    """Complete observation processor that combines image and state processing.
+
+    This processor replicates the functionality of the original preprocess_observation
+    function but in a modular, composable way that fits into the pipeline architecture.
+    """
+
+    image_processor: ImageProcessor = field(default_factory=ImageProcessor)
+    state_processor: StateProcessor = field(default_factory=StateProcessor)
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        # First process images
+        transition = self.image_processor(transition)
+        # Then process state
+        transition = self.state_processor(transition)
+        return transition
+
+    def get_config(self) -> dict[str, Any]:
+        """Return configuration for serialization."""
+        return {
+            "image_processor": self.image_processor.get_config(),
+            "state_processor": self.state_processor.get_config(),
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        """Return state dictionary."""
+        state = {}
+        state.update({f"image_processor.{k}": v for k, v in self.image_processor.state_dict().items()})
+        state.update({f"state_processor.{k}": v for k, v in self.state_processor.state_dict().items()})
+        return state
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        """Load state dictionary."""
+        image_state = {
+            k.replace("image_processor.", ""): v for k, v in state.items() if k.startswith("image_processor.")
+        }
+        state_state = {
+            k.replace("state_processor.", ""): v for k, v in state.items() if k.startswith("state_processor.")
+        }
+
+        self.image_processor.load_state_dict(image_state)
+        self.state_processor.load_state_dict(state_state)
+
+    def reset(self) -> None:
+        """Reset processor state."""
+        self.image_processor.reset()
+        self.state_processor.reset()
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        features = self.image_processor.feature_contract(features)
+        features = self.state_processor.feature_contract(features)
         return features

src/lerobot/processor/pipeline.py

@@ -31,12 +31,12 @@ from huggingface_hub.errors import HfHubHTTPError
 from safetensors.torch import load_file, save_file
 
 from lerobot.configs.types import PolicyFeature
+from lerobot.utils.utils import get_safe_torch_device
 
 
 class TransitionKey(str, Enum):
     """Keys for accessing EnvTransition dictionary components."""
 
-    # TODO(Steven): Use consts
     OBSERVATION = "observation"
     ACTION = "action"
     REWARD = "reward"
@@ -46,18 +46,19 @@ class TransitionKey(str, Enum):
     COMPLEMENTARY_DATA = "complementary_data"
 
 
-EnvTransition = TypedDict(
-    "EnvTransition",
-    {
-        TransitionKey.OBSERVATION.value: dict[str, Any] | None,
-        TransitionKey.ACTION.value: Any | torch.Tensor | None,
-        TransitionKey.REWARD.value: float | torch.Tensor | None,
-        TransitionKey.DONE.value: bool | torch.Tensor | None,
-        TransitionKey.TRUNCATED.value: bool | torch.Tensor | None,
-        TransitionKey.INFO.value: dict[str, Any] | None,
-        TransitionKey.COMPLEMENTARY_DATA.value: dict[str, Any] | None,
-    },
-)
+class EnvTransition(TypedDict, total=False):
+    """Environment transition data structure.
+
+    All fields are optional (total=False) to allow flexible usage.
+    """
+
+    observation: dict[str, Any] | None
+    action: Any | torch.Tensor | None
+    reward: float | torch.Tensor | None
+    done: bool | torch.Tensor | None
+    truncated: bool | torch.Tensor | None
+    info: dict[str, Any] | None
+    complementary_data: dict[str, Any] | None
 
 
 class ProcessorStepRegistry:
@@ -135,8 +136,8 @@ class ProcessorStepRegistry:
 class ProcessorStep(Protocol):
     """Structural typing interface for a single processor step.
 
-    A step is any callable accepting a full `EnvTransition` dict and
-    returning a (possibly modified) dict of the same structure. Implementers
+    A step is any callable accepting a full `EnvTransition` tuple and
+    returning a (possibly modified) tuple of the same structure. Implementers
     are encouraged—but not required—to expose the optional helper methods
     listed below. When present, these hooks let `RobotProcessor`
     automatically serialise the step's configuration and learnable state using
@@ -254,22 +255,24 @@ class RobotProcessor(ModelHubMixin):
     Composable, debuggable post-processing processor for robot transitions.
 
     The class orchestrates an ordered collection of small, functional transforms—steps—executed
-    left-to-right on each incoming `EnvTransition`. It can process both `EnvTransition` dicts
+    left-to-right on each incoming `EnvTransition`. It can process both `EnvTransition` tuples
     and batch dictionaries, automatically converting between formats as needed.
 
     Args:
         steps: Ordered list of processing steps executed on every call. Defaults to empty list.
         name: Human-readable identifier that is persisted inside the JSON config.
             Defaults to "RobotProcessor".
-        to_transition: Function to convert batch dict to EnvTransition dict.
+        seed: Global seed forwarded to steps that choose to consume it. Defaults to None.
+        to_transition: Function to convert batch dict to EnvTransition tuple.
             Defaults to _default_batch_to_transition.
-        to_output: Function to convert EnvTransition dict to the desired output format.
-            Usually it is a batch dict or EnvTransition dict.
+        to_output: Function to convert EnvTransition tuple to the desired output format.
+            Usually it is a batch dict or EnvTransition tuple.
             Defaults to _default_transition_to_batch.
         before_step_hooks: List of hooks called before each step. Each hook receives the step
             index and transition, and can optionally return a modified transition.
         after_step_hooks: List of hooks called after each step. Each hook receives the step
             index and transition, and can optionally return a modified transition.
+        reset_hooks: List of hooks called during processor reset.
 
     Hook Semantics:
         - Hooks are executed sequentially in the order they were registered. There is no way to
@@ -281,13 +284,11 @@ class RobotProcessor(ModelHubMixin):
         - Hooks should generally be stateless to maintain predictable behavior. If you need stateful
           processing, consider implementing a proper ProcessorStep instead.
         - To remove hooks, use the unregister methods. To remove steps, you must create a new pipeline.
-        - Hooks ALWAYS receive transitions in EnvTransition format, regardless of the input format
-          passed to __call__. This ensures consistent hook behavior whether processing batch dicts
-          or EnvTransition objects.
     """
 
     steps: Sequence[ProcessorStep] = field(default_factory=list)
     name: str = "RobotProcessor"
+    seed: int | None = None
 
     to_transition: Callable[[dict[str, Any]], EnvTransition] = field(
         default_factory=lambda: _default_batch_to_transition, repr=False
@@ -300,6 +301,7 @@ class RobotProcessor(ModelHubMixin):
     # Hooks do not modify transitions - they are called for logging, debugging, or monitoring purposes
     before_step_hooks: list[Callable[[int, EnvTransition], None]] = field(default_factory=list, repr=False)
     after_step_hooks: list[Callable[[int, EnvTransition], None]] = field(default_factory=list, repr=False)
+    reset_hooks: list[Callable[[], None]] = field(default_factory=list, repr=False)
 
     def __call__(self, data: EnvTransition | dict[str, Any]):
         """Process data through all steps.
@@ -319,30 +321,22 @@ class RobotProcessor(ModelHubMixin):
         Raises:
             ValueError: If the transition is not a valid EnvTransition format.
         """
-        # Check if we need to convert back to batch format at the end
-        _, called_with_batch = self._prepare_transition(data)
+        iterator = self.step_through(data)
+        current_result = next(iterator)  # Get initial state
 
-        # Use step_through to get the iterator
-        step_iterator = self.step_through(data)
-
-        # Get initial state (before any steps)
-        current_transition = next(step_iterator)
-
-        # Process each step with hooks
-        for idx, next_transition in enumerate(step_iterator):
-            # Apply before hooks with current state (before step execution)
+        # Process through all steps with hooks
+        for idx, step_result in enumerate(iterator):
+            # Apply before hooks
             for hook in self.before_step_hooks:
-                hook(idx, current_transition)
+                _ = hook(idx, step_result)
 
-            # Move to next state (after step execution)
-            current_transition = next_transition
-
-            # Apply after hooks with updated state
+            # Apply after hooks
             for hook in self.after_step_hooks:
-                hook(idx, current_transition)
+                _ = hook(idx, step_result)
 
-        # Convert back to original format if needed
-        return self.to_output(current_transition) if called_with_batch else current_transition
+            current_result = step_result
+
+        return current_result
 
     def _prepare_transition(self, data: EnvTransition | dict[str, Any]) -> tuple[EnvTransition, bool]:
         """Prepare and validate transition data for processing.
@@ -372,48 +366,64 @@ class RobotProcessor(ModelHubMixin):
 
         return transition, called_with_batch
 
-    def step_through(self, data: EnvTransition | dict[str, Any]) -> Iterable[EnvTransition]:
+    def step_through(self, data: EnvTransition | dict[str, Any]) -> Iterable[EnvTransition | dict[str, Any]]:
         """Yield the intermediate results after each processor step.
 
         This is a low-level method that does NOT apply hooks. It simply executes each step
         and yields the intermediate results. This allows users to debug the pipeline or
         apply custom logic between steps if needed.
 
-        Note: This method always yields EnvTransition objects regardless of input format.
-        If you need the results in the original input format, you'll need to convert them
-        using `to_output()`.
+        Like __call__, this method accepts either EnvTransition dicts or batch dictionaries
+        and preserves the input format in the yielded results.
 
         Args:
             data: Either an EnvTransition dict or a batch dictionary to process.
 
         Yields:
-            The intermediate EnvTransition results after each step.
+            The intermediate results after each step, in the same format as the input.
         """
-        transition, _ = self._prepare_transition(data)
+        transition, called_with_batch = self._prepare_transition(data)
 
         # Yield initial state
-        yield transition
+        yield self.to_output(transition) if called_with_batch else transition
 
         # Process each step WITHOUT hooks (low-level method)
         for processor_step in self.steps:
             transition = processor_step(transition)
-            yield transition
+            yield self.to_output(transition) if called_with_batch else transition
 
-    def _save_pretrained(self, save_directory: Path, **kwargs):
+    def _save_pretrained(self, destination_path: str, **kwargs):
         """Internal save method for ModelHubMixin compatibility."""
         # Extract config_filename from kwargs if provided
         config_filename = kwargs.pop("config_filename", None)
-        self.save_pretrained(save_directory, config_filename=config_filename)
+        self.save_pretrained(destination_path, config_filename=config_filename)
 
-    def save_pretrained(self, save_directory: str | Path, config_filename: str | None = None, **kwargs):
-        """Serialize the processor definition and parameters to *save_directory*.
+    def _generate_model_card(self, destination_path: str) -> None:
+        """Generate README.md from the RobotProcessor model card template."""
+        # Read the template
+        template_path = Path(__file__).parent.parent / "templates" / "robotprocessor_modelcard_template.md"
+
+        if not template_path.exists():
+            # Fallback: if template doesn't exist, skip model card generation
+            return
+
+        with open(template_path) as f:
+            model_card_content = f.read()
+
+        # Write the README.md
+        readme_path = os.path.join(destination_path, "README.md")
+        with open(readme_path, "w") as f:
+            f.write(model_card_content)
+
+    def save_pretrained(self, destination_path: str, config_filename: str | None = None, **kwargs):
+        """Serialize the processor definition and parameters to *destination_path*.
 
         Args:
-            save_directory: Directory where the processor will be saved.
+            destination_path: Directory where the processor will be saved.
             config_filename: Optional custom config filename. If not provided, defaults to
                 "{self.name}.json" where self.name is sanitized for filesystem compatibility.
         """
-        os.makedirs(str(save_directory), exist_ok=True)
+        os.makedirs(destination_path, exist_ok=True)
 
         # Sanitize processor name for use in filenames
         import re
@@ -427,6 +437,7 @@ class RobotProcessor(ModelHubMixin):
 
         config: dict[str, Any] = {
             "name": self.name,
+            "seed": self.seed,
             "steps": [],
         }
 
@@ -434,15 +445,16 @@ class RobotProcessor(ModelHubMixin):
             # Check if step was registered
             registry_name = getattr(processor_step.__class__, "_registry_name", None)
 
-            step_entry: dict[str, Any] = {}
             if registry_name:
                 # Use registry name for registered steps
-                step_entry["registry_name"] = registry_name
+                step_entry: dict[str, Any] = {
+                    "registry_name": registry_name,
+                }
             else:
                 # Fall back to full module path for unregistered steps
-                step_entry["class"] = (
-                    f"{processor_step.__class__.__module__}.{processor_step.__class__.__name__}"
-                )
+                step_entry: dict[str, Any] = {
+                    "class": f"{processor_step.__class__.__module__}.{processor_step.__class__.__name__}",
+                }
 
             if hasattr(processor_step, "get_config"):
                 step_entry["config"] = processor_step.get_config()
@@ -469,34 +481,43 @@ class RobotProcessor(ModelHubMixin):
                     else:
                         state_filename = f"{sanitized_name}_step_{step_index}.safetensors"
 
-                    save_file(cloned_state, os.path.join(str(save_directory), state_filename))
+                    save_file(cloned_state, os.path.join(destination_path, state_filename))
                     step_entry["state_file"] = state_filename
 
             config["steps"].append(step_entry)
 
-        with open(os.path.join(str(save_directory), config_filename), "w") as file_pointer:
+        with open(os.path.join(destination_path, config_filename), "w") as file_pointer:
             json.dump(config, file_pointer, indent=2)
 
+        # Generate README.md from template
+        self._generate_model_card(destination_path)
+
+    def to(self, device: str | torch.device):
+        """Move all tensor states inside each step to device and return self.
+
+        Uses a generic mechanism: fetch each step's state dict, move every tensor
+        to the target device, and reload it. Only works for steps that implement
+        both state_dict() and load_state_dict() methods.
+        """
+        device = get_safe_torch_device(device)
+
+        for step in self.steps:
+            if hasattr(step, "state_dict") and hasattr(step, "load_state_dict"):
+                state = step.state_dict()
+                if state:  # Only process if there's actual state
+                    moved_state = {k: v.to(device) for k, v in state.items()}
+                    step.load_state_dict(moved_state)
+
+        return self
+
     @classmethod
     def from_pretrained(
-        cls,
-        pretrained_model_name_or_path: str | Path,
-        *,
-        force_download: bool = False,
-        resume_download: bool | None = None,
-        proxies: dict[str, str] | None = None,
-        token: str | bool | None = None,
-        cache_dir: str | Path | None = None,
-        local_files_only: bool = False,
-        revision: str | None = None,
-        config_filename: str | None = None,
-        overrides: dict[str, Any] | None = None,
-        **kwargs,
+        cls, source: str, *, config_filename: str | None = None, overrides: dict[str, Any] | None = None
     ) -> RobotProcessor:
         """Load a serialized processor from source (local path or Hugging Face Hub identifier).
 
         Args:
-            pretrained_model_name_or_path: Local path to a saved processor directory or Hugging Face Hub identifier
+            source: Local path to a saved processor directory or Hugging Face Hub identifier
                 (e.g., "username/processor-name").
             config_filename: Optional specific config filename to load. If not provided, will:
                 - For local paths: look for any .json file in the directory (error if multiple found)
@@ -549,9 +570,6 @@ class RobotProcessor(ModelHubMixin):
             )
             ```
         """
-        # Use the local variable name 'source' for clarity
-        source = str(pretrained_model_name_or_path)
-
         if Path(source).is_dir():
             # Local path - use it directly
             base_path = Path(source)
@@ -569,7 +587,7 @@ class RobotProcessor(ModelHubMixin):
                 config_filename = json_files[0].name
 
             with open(base_path / config_filename) as file_pointer:
-                loaded_config: dict[str, Any] = json.load(file_pointer)
+                config: dict[str, Any] = json.load(file_pointer)
         else:
             # Hugging Face Hub - download all required files
             if config_filename is None:
@@ -583,18 +601,7 @@ class RobotProcessor(ModelHubMixin):
                 config_path = None
                 for name in common_names:
                     try:
-                        config_path = hf_hub_download(
-                            source,
-                            name,
-                            repo_type="model",
-                            force_download=force_download,
-                            resume_download=resume_download,
-                            proxies=proxies,
-                            token=token,
-                            cache_dir=cache_dir,
-                            local_files_only=local_files_only,
-                            revision=revision,
-                        )
+                        config_path = hf_hub_download(source, name, repo_type="model")
                         config_filename = name
                         break
                     except (FileNotFoundError, OSError, HfHubHTTPError):
@@ -610,21 +617,10 @@ class RobotProcessor(ModelHubMixin):
                     )
             else:
                 # Download specific config file
-                config_path = hf_hub_download(
-                    source,
-                    config_filename,
-                    repo_type="model",
-                    force_download=force_download,
-                    resume_download=resume_download,
-                    proxies=proxies,
-                    token=token,
-                    cache_dir=cache_dir,
-                    local_files_only=local_files_only,
-                    revision=revision,
-                )
+                config_path = hf_hub_download(source, config_filename, repo_type="model")
 
             with open(config_path) as file_pointer:
-                loaded_config = json.load(file_pointer)
+                config: dict[str, Any] = json.load(file_pointer)
 
             # Store downloaded files in the same directory as the config
             base_path = Path(config_path).parent
@@ -637,7 +633,7 @@ class RobotProcessor(ModelHubMixin):
         override_keys = set(overrides.keys())
 
         steps: list[ProcessorStep] = []
-        for step_entry in loaded_config["steps"]:
+        for step_entry in config["steps"]:
             # Check if step uses registry name or module path
             if "registry_name" in step_entry:
                 # Load from registry
@@ -689,18 +685,7 @@ class RobotProcessor(ModelHubMixin):
                     state_path = str(base_path / step_entry["state_file"])
                 else:
                     # Hugging Face Hub - download the state file
-                    state_path = hf_hub_download(
-                        source,
-                        step_entry["state_file"],
-                        repo_type="model",
-                        force_download=force_download,
-                        resume_download=resume_download,
-                        proxies=proxies,
-                        token=token,
-                        cache_dir=cache_dir,
-                        local_files_only=local_files_only,
-                        revision=revision,
-                    )
+                    state_path = hf_hub_download(source, step_entry["state_file"], repo_type="model")
 
                 step_instance.load_state_dict(load_file(state_path))
 
@@ -709,7 +694,7 @@ class RobotProcessor(ModelHubMixin):
         # Check for unused override keys
         if override_keys:
             available_keys = []
-            for step_entry in loaded_config["steps"]:
+            for step_entry in config["steps"]:
                 if "registry_name" in step_entry:
                     available_keys.append(step_entry["registry_name"])
                 else:
@@ -723,7 +708,7 @@ class RobotProcessor(ModelHubMixin):
                 f"Make sure override keys match exact step class names or registry names."
             )
 
-        return cls(steps, loaded_config.get("name", "RobotProcessor"))
+        return cls(steps, config.get("name", "RobotProcessor"), config.get("seed"))
 
     def __len__(self) -> int:
         """Return the number of steps in the processor."""
@@ -735,7 +720,7 @@ class RobotProcessor(ModelHubMixin):
         * ``slice`` – returns a new RobotProcessor with the sliced steps.
         """
         if isinstance(idx, slice):
-            return RobotProcessor(self.steps[idx], self.name)
+            return RobotProcessor(self.steps[idx], self.name, self.seed)
         return self.steps[idx]
 
     def register_before_step_hook(self, fn: Callable[[int, EnvTransition], None]):
@@ -778,11 +763,71 @@ class RobotProcessor(ModelHubMixin):
                 f"Hook {fn} not found in after_step_hooks. Make sure to pass the exact same function reference."
             ) from None
 
+    def register_reset_hook(self, fn: Callable[[], None]):
+        """Attach fn to be executed when reset is called."""
+        self.reset_hooks.append(fn)
+
+    def unregister_reset_hook(self, fn: Callable[[], None]):
+        """Remove a previously registered reset hook.
+
+        Args:
+            fn: The exact function reference that was registered. Must be the same object.
+
+        Raises:
+            ValueError: If the hook is not found in the registered hooks.
+        """
+        try:
+            self.reset_hooks.remove(fn)
+        except ValueError:
+            raise ValueError(
+                f"Hook {fn} not found in reset_hooks. Make sure to pass the exact same function reference."
+            ) from None
+
     def reset(self):
         """Clear state in every step that implements ``reset()`` and fire registered hooks."""
         for step in self.steps:
             if hasattr(step, "reset"):
                 step.reset()  # type: ignore[attr-defined]
+        for fn in self.reset_hooks:
+            fn()
+
+    def profile_steps(
+        self, transition: EnvTransition, num_runs: int = 100, warmup_runs: int = 5
+    ) -> dict[str, float]:
+        """Profile the execution time of each step for performance optimization."""
+        import copy
+        import time
+
+        profile_results = {}
+
+        # Make a copy to avoid altering the original transition
+        transition_copy = copy.deepcopy(transition)
+
+        # Get intermediate transitions for each step using step_through
+        intermediate_transitions = list(self.step_through(transition_copy))
+
+        for idx, processor_step in enumerate(self.steps):
+            step_name = f"step_{idx}_{processor_step.__class__.__name__}"
+
+            # Use the appropriate input transition for this step
+            input_transition = intermediate_transitions[idx]
+
+            # Warm up - copy transition for each run to ensure consistent conditions
+            for _ in range(warmup_runs):
+                transition_copy = copy.deepcopy(input_transition)
+                _ = processor_step(transition_copy)
+
+            # Time the step - copy transition for each run to ensure consistent conditions
+            start_time = time.perf_counter()
+            for _ in range(num_runs):
+                transition_copy = copy.deepcopy(input_transition)
+                _ = processor_step(transition_copy)
+            end_time = time.perf_counter()
+
+            avg_time = (end_time - start_time) / num_runs * 1000  # Convert to milliseconds
+            profile_results[step_name] = avg_time
+
+        return profile_results
 
     def __repr__(self) -> str:
         """Return a readable string representation of the processor."""
@@ -799,6 +844,9 @@ class RobotProcessor(ModelHubMixin):
 
         parts = [f"name='{self.name}'", steps_repr]
 
+        if self.seed is not None:
+            parts.append(f"seed={self.seed}")
+
         return f"RobotProcessor({', '.join(parts)})"
 
     def __post_init__(self):
@@ -863,30 +911,12 @@ class ObservationProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         observation = transition.get(TransitionKey.OBSERVATION)
-        if observation is None:
-            return transition
-
         processed_observation = self.observation(observation)
         # Create a new transition dict with the processed observation
         new_transition = transition.copy()
         new_transition[TransitionKey.OBSERVATION] = processed_observation
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class ActionProcessor:
     """Base class for processors that modify only the action component of a transition.
@@ -923,30 +953,12 @@ class ActionProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         action = transition.get(TransitionKey.ACTION)
-        if action is None:
-            return transition
-
         processed_action = self.action(action)
         # Create a new transition dict with the processed action
         new_transition = transition.copy()
         new_transition[TransitionKey.ACTION] = processed_action
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class RewardProcessor:
     """Base class for processors that modify only the reward component of a transition.
@@ -982,30 +994,12 @@ class RewardProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         reward = transition.get(TransitionKey.REWARD)
-        if reward is None:
-            return transition
-
         processed_reward = self.reward(reward)
         # Create a new transition dict with the processed reward
         new_transition = transition.copy()
         new_transition[TransitionKey.REWARD] = processed_reward
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class DoneProcessor:
     """Base class for processors that modify only the done flag of a transition.
@@ -1046,30 +1040,12 @@ class DoneProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         done = transition.get(TransitionKey.DONE)
-        if done is None:
-            return transition
-
         processed_done = self.done(done)
         # Create a new transition dict with the processed done flag
         new_transition = transition.copy()
         new_transition[TransitionKey.DONE] = processed_done
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class TruncatedProcessor:
     """Base class for processors that modify only the truncated flag of a transition.
@@ -1106,30 +1082,12 @@ class TruncatedProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         truncated = transition.get(TransitionKey.TRUNCATED)
-        if truncated is None:
-            return transition
-
         processed_truncated = self.truncated(truncated)
         # Create a new transition dict with the processed truncated flag
         new_transition = transition.copy()
         new_transition[TransitionKey.TRUNCATED] = processed_truncated
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class InfoProcessor:
     """Base class for processors that modify only the info dictionary of a transition.
@@ -1171,30 +1129,12 @@ class InfoProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         info = transition.get(TransitionKey.INFO)
-        if info is None:
-            return transition
-
         processed_info = self.info(info)
         # Create a new transition dict with the processed info
         new_transition = transition.copy()
         new_transition[TransitionKey.INFO] = processed_info
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class ComplementaryDataProcessor:
     """Base class for processors that modify only the complementary data of a transition.
@@ -1217,30 +1157,12 @@ class ComplementaryDataProcessor:
 
     def __call__(self, transition: EnvTransition) -> EnvTransition:
         complementary_data = transition.get(TransitionKey.COMPLEMENTARY_DATA)
-        if complementary_data is None:
-            return transition
-
         processed_complementary_data = self.complementary_data(complementary_data)
         # Create a new transition dict with the processed complementary data
         new_transition = transition.copy()
         new_transition[TransitionKey.COMPLEMENTARY_DATA] = processed_complementary_data
         return new_transition
 
-    def get_config(self) -> dict[str, Any]:
-        return {}
-
-    def state_dict(self) -> dict[str, torch.Tensor]:
-        return {}
-
-    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
-        pass
-
-    def reset(self) -> None:
-        pass
-
-    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
-        return features
-
 
 class IdentityProcessor:
     """Identity processor that does nothing."""

src/lerobot/processor/rename_processor.py

@@ -16,21 +16,24 @@
 from dataclasses import dataclass, field
 from typing import Any
 
+import torch
+
 from lerobot.configs.types import PolicyFeature
-from lerobot.processor.pipeline import (
-    ObservationProcessor,
-    ProcessorStepRegistry,
-)
+from lerobot.processor.pipeline import EnvTransition, ProcessorStepRegistry, TransitionKey
 
 
 @dataclass
 @ProcessorStepRegistry.register(name="rename_processor")
-class RenameProcessor(ObservationProcessor):
+class RenameProcessor:
     """Rename processor that renames keys in the observation."""
 
     rename_map: dict[str, str] = field(default_factory=dict)
 
-    def observation(self, observation):
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+        if observation is None:
+            return transition
+
         processed_obs = {}
         for key, value in observation.items():
             if key in self.rename_map:
@@ -38,11 +41,20 @@ class RenameProcessor(ObservationProcessor):
             else:
                 processed_obs[key] = value
 
-        return processed_obs
+        # Create a new transition with the renamed observation
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = processed_obs
+        return new_transition
 
     def get_config(self) -> dict[str, Any]:
         return {"rename_map": self.rename_map}
 
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
     def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
         """Transforms:
         - Each key in the observation that appears in `rename_map` is renamed to its value.

src/lerobot/processor/robot_processor.py

@@ -0,0 +1,245 @@
+from dataclasses import dataclass, field
+from typing import Any
+
+import gymnasium as gym
+import numpy as np
+import torch
+
+from lerobot.configs.types import PolicyFeature
+from lerobot.model.kinematics import RobotKinematics
+from lerobot.processor.pipeline import EnvTransition, ProcessorStepRegistry, TransitionKey
+
+
+@dataclass
+@ProcessorStepRegistry.register("joint_velocity_processor")
+class JointVelocityProcessor:
+    """Add joint velocity information to observations.
+
+    Computes joint velocities by tracking changes in joint positions over time.
+    """
+
+    joint_velocity_limits: float = 100.0
+    dt: float = 1.0 / 10
+
+    last_joint_positions: torch.Tensor | None = None
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+        if observation is None:
+            return transition
+
+        # Get current joint positions (assuming they're in observation.state)
+        current_positions = observation.get("observation.state")
+        if current_positions is None:
+            return transition
+
+        # Initialize last joint positions if not already set
+        if self.last_joint_positions is None:
+            self.last_joint_positions = current_positions.clone()
+
+        # Compute velocities
+        joint_velocities = (current_positions - self.last_joint_positions) / self.dt
+        self.last_joint_positions = current_positions.clone()
+
+        # Extend observation with velocities
+        extended_state = torch.cat([current_positions, joint_velocities], dim=-1)
+
+        # Create new observation dict
+        new_observation = dict(observation)
+        new_observation["observation.state"] = extended_state
+
+        # Return new transition
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = new_observation
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "joint_velocity_limits": self.joint_velocity_limits,
+            "dt": self.dt,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        self.last_joint_positions = None
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("current_processor")
+class MotorCurrentProcessor:
+    """Add motor current information to observations."""
+
+    env: gym.Env = None
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        observation = transition.get(TransitionKey.OBSERVATION)
+        if observation is None:
+            return transition
+
+        # Get current values from complementary_data (where robot state would be stored)
+        present_current_dict = self.env.unwrapped.robot.bus.sync_read("Present_Current")
+        motor_currents = torch.tensor(
+            [present_current_dict[name] for name in self.env.unwrapped.robot.bus.motors],
+            dtype=torch.float32,
+        ).unsqueeze(0)
+
+        current_state = observation.get("observation.state")
+        if current_state is None:
+            return transition
+
+        extended_state = torch.cat([current_state, motor_currents], dim=-1)
+
+        # Create new observation dict
+        new_observation = dict(observation)
+        new_observation["observation.state"] = extended_state
+
+        # Return new transition
+        new_transition = transition.copy()
+        new_transition[TransitionKey.OBSERVATION] = new_observation
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {}
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        pass
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features
+
+
+@dataclass
+@ProcessorStepRegistry.register("inverse_kinematics_processor")
+class InverseKinematicsProcessor:
+    """Convert end-effector space actions to joint space using inverse kinematics.
+
+    This processor transforms delta commands in end-effector space (delta_x, delta_y, delta_z)
+    to joint space commands using forward and inverse kinematics. It maintains the current
+    end-effector pose and joint positions to compute the transformations.
+    """
+
+    urdf_path: str
+    target_frame_name: str = "gripper_link"
+    end_effector_step_sizes: dict[str, float] = field(default_factory=lambda: {"x": 1.0, "y": 1.0, "z": 1.0})
+    end_effector_bounds: dict[str, list[float]] | None = None
+    max_gripper_pos: float = 30.0
+
+    # State tracking
+    current_ee_pos: np.ndarray | None = field(default=None, init=False, repr=False)
+    current_joint_pos: np.ndarray | None = field(default=None, init=False, repr=False)
+    kinematics: RobotKinematics | None = field(default=None, init=False, repr=False)
+
+    def __post_init__(self):
+        """Initialize the kinematics module after dataclass initialization."""
+        if self.urdf_path:
+            self.kinematics = RobotKinematics(
+                urdf_path=self.urdf_path,
+                target_frame_name=self.target_frame_name,
+            )
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        action = transition.get(TransitionKey.ACTION)
+        if action is None:
+            return transition
+
+        action_np = action.detach().cpu().numpy().squeeze()
+
+        complementary_data = transition.get(TransitionKey.COMPLEMENTARY_DATA, {})
+        raw_joint_positions = complementary_data.get("raw_joint_positions")
+        current_gripper_pos = raw_joint_positions[-1]
+        if self.current_joint_pos is None:
+            self.current_joint_pos = raw_joint_positions
+
+        # Initialize end-effector position if not available
+        if self.current_joint_pos is None:
+            return transition  # Cannot proceed without joint positions
+
+        # Calculate current end-effector position using forward kinematics
+        if self.current_ee_pos is None:
+            self.current_ee_pos = self.kinematics.forward_kinematics(self.current_joint_pos)
+
+        # Scale deltas by step sizes
+        delta_ee = np.array(
+            [
+                action_np[0] * self.end_effector_step_sizes["x"],
+                action_np[1] * self.end_effector_step_sizes["y"],
+                action_np[2] * self.end_effector_step_sizes["z"],
+            ],
+            dtype=np.float32,
+        )
+
+        # Set desired end-effector position by adding delta
+        desired_ee_pos = np.eye(4)
+        desired_ee_pos[:3, :3] = self.current_ee_pos[:3, :3]  # Keep orientation
+
+        # Add delta to position and clip to bounds
+        desired_ee_pos[:3, 3] = self.current_ee_pos[:3, 3] + delta_ee
+        if self.end_effector_bounds is not None:
+            desired_ee_pos[:3, 3] = np.clip(
+                desired_ee_pos[:3, 3],
+                self.end_effector_bounds["min"],
+                self.end_effector_bounds["max"],
+            )
+
+        # Compute inverse kinematics to get joint positions
+        target_joint_values = self.kinematics.inverse_kinematics(self.current_joint_pos, desired_ee_pos)
+
+        # Update current state
+        self.current_ee_pos = desired_ee_pos.copy()
+        self.current_joint_pos = target_joint_values.copy()
+
+        # Create new action with joint space commands
+        gripper_action = current_gripper_pos
+        if len(action_np) > 3:
+            # Handle gripper command separately
+            gripper_command = action_np[3]
+
+            # Process gripper command (convert from [0,2] to delta) and discretize
+            gripper_delta = np.round(gripper_command - 1.0).astype(int) * self.max_gripper_pos
+            gripper_action = np.clip(current_gripper_pos + gripper_delta, 0, self.max_gripper_pos)
+
+        # Combine joint positions and gripper
+        target_joint_values[-1] = gripper_action
+
+        converted_action = torch.from_numpy(target_joint_values).to(action.device).to(action.dtype)
+
+        new_transition = transition.copy()
+        new_transition[TransitionKey.ACTION] = converted_action
+        return new_transition
+
+    def get_config(self) -> dict[str, Any]:
+        return {
+            "urdf_path": self.urdf_path,
+            "target_frame_name": self.target_frame_name,
+            "end_effector_step_sizes": self.end_effector_step_sizes,
+            "end_effector_bounds": self.end_effector_bounds,
+            "max_gripper_pos": self.max_gripper_pos,
+        }
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        return {}
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        pass
+
+    def reset(self) -> None:
+        """Reset the processor state."""
+        self.current_ee_pos = None
+        self.current_joint_pos = None
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        return features

src/lerobot/record.py

@@ -18,7 +18,7 @@ Records a dataset. Actions for the robot can be either generated by teleoperatio
 Example:
 
 ```shell
-lerobot-record \
+python -m lerobot.record \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.cameras="{laptop: {type: opencv, camera_index: 0, width: 640, height: 480}}" \
@@ -36,7 +36,7 @@ lerobot-record \
 
 Example recording with bimanual so100:
 ```shell
-lerobot-record \
+python -m lerobot.record \
   --robot.type=bi_so100_follower \
   --robot.left_arm_port=/dev/tty.usbmodem5A460851411 \
   --robot.right_arm_port=/dev/tty.usbmodem5A460812391 \
@@ -393,9 +393,5 @@ def record(cfg: RecordConfig) -> LeRobotDataset:
     return dataset
 
 
-def main():
-    record()
-
-
 if __name__ == "__main__":
-    main()
+    record()

src/lerobot/replay.py

@@ -18,7 +18,7 @@ Replays the actions of an episode from a dataset on a robot.
 Examples:
 
 ```shell
-lerobot-replay \
+python -m lerobot.replay \
     --robot.type=so100_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.id=black \
@@ -28,7 +28,7 @@ lerobot-replay \
 
 Example replay with bimanual so100:
 ```shell
-lerobot-replay \
+python -m lerobot.replay \
   --robot.type=bi_so100_follower \
   --robot.left_arm_port=/dev/tty.usbmodem5A460851411 \
   --robot.right_arm_port=/dev/tty.usbmodem5A460812391 \
@@ -112,9 +112,5 @@ def replay(cfg: ReplayConfig):
     robot.disconnect()
 
 
-def main():
-    replay()
-
-
 if __name__ == "__main__":
-    main()
+    replay()

src/lerobot/robots/so100_follower/so100_follower.py

@@ -161,11 +161,6 @@ class SO100Follower(Robot):
                 self.bus.write("I_Coefficient", motor, 0)
                 self.bus.write("D_Coefficient", motor, 32)
 
-                if motor == "gripper":
-                    self.bus.write("Max_Torque_Limit", motor, 500)  # 50% of max torque to avoid burnout
-                    self.bus.write("Protection_Current", motor, 250)  # 50% of max current to avoid burnout
-                    self.bus.write("Overload_Torque", motor, 25)  # 25% torque when overloaded
-
     def setup_motors(self) -> None:
         for motor in reversed(self.bus.motors):
             input(f"Connect the controller board to the '{motor}' motor only and press enter.")

src/lerobot/robots/so101_follower/so101_follower.py

@@ -157,13 +157,6 @@ class SO101Follower(Robot):
                 self.bus.write("I_Coefficient", motor, 0)
                 self.bus.write("D_Coefficient", motor, 32)
 
-                if motor == "gripper":
-                    self.bus.write(
-                        "Max_Torque_Limit", motor, 500
-                    )  # 50% of the max torque limit to avoid burnout
-                    self.bus.write("Protection_Current", motor, 250)  # 50% of max current to avoid burnout
-                    self.bus.write("Overload_Torque", motor, 25)  # 25% torque when overloaded
-
     def setup_motors(self) -> None:
         for motor in reversed(self.bus.motors):
             input(f"Connect the controller board to the '{motor}' motor only and press enter.")

src/lerobot/robots/viperx/README.md

@@ -141,10 +141,10 @@ python lerobot/scripts/control_robot.py \
 
 ## Train a policy
 
-To train a policy to control your robot, use the [`lerobot-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`](../src/lerobot/scripts/train.py) script. A few arguments are required. Here is an example command:
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --dataset.repo_id=${HF_USER}/aloha_test \
   --policy.type=act \
   --output_dir=outputs/train/act_aloha_test \

src/lerobot/scripts/eval.py

@@ -21,7 +21,7 @@ You want to evaluate a model from the hub (eg: https://huggingface.co/lerobot/di
 for 10 episodes.
 
 ```
-lerobot-eval \
+python -m lerobot.scripts.eval \
     --policy.path=lerobot/diffusion_pusht \
     --env.type=pusht \
     --eval.batch_size=10 \
@@ -32,7 +32,7 @@ lerobot-eval \
 
 OR, you want to evaluate a model checkpoint from the LeRobot training script for 10 episodes.
 ```
-lerobot-eval \
+python -m lerobot.scripts.eval \
     --policy.path=outputs/train/diffusion_pusht/checkpoints/005000/pretrained_model \
     --env.type=pusht \
     --eval.batch_size=10 \
@@ -68,10 +68,11 @@ from tqdm import trange
 from lerobot.configs import parser
 from lerobot.configs.eval import EvalPipelineConfig
 from lerobot.envs.factory import make_env
-from lerobot.envs.utils import add_envs_task, check_env_attributes_and_types, preprocess_observation
+from lerobot.envs.utils import add_envs_task, check_env_attributes_and_types
 from lerobot.policies.factory import make_policy
 from lerobot.policies.pretrained import PreTrainedPolicy
 from lerobot.policies.utils import get_device_from_parameters
+from lerobot.processor import RobotProcessor, TransitionKey, VanillaObservationProcessor
 from lerobot.utils.io_utils import write_video
 from lerobot.utils.random_utils import set_seed
 from lerobot.utils.utils import (
@@ -128,6 +129,16 @@ def rollout(
     if render_callback is not None:
         render_callback(env)
 
+    # Create observation processing processor
+    # NOTE: During environment interaction, we skip batch dictionary conversion
+    # since that format is only needed for loss computation during training.
+    # Using identity functions to avoid unnecessary format transformations.
+    obs_processor = RobotProcessor(
+        [VanillaObservationProcessor()],
+        to_transition=lambda x: x,
+        to_output=lambda x: x,
+    )
+
     all_observations = []
     all_actions = []
     all_rewards = []
@@ -147,10 +158,13 @@ def rollout(
     check_env_attributes_and_types(env)
     while not np.all(done):
         # Numpy array to tensor and changing dictionary keys to LeRobot policy format.
-        observation = preprocess_observation(observation)
+        transition = (observation, None, None, None, None, None, None)
+        processed_transition = obs_processor(transition)
+        observation = processed_transition[TransitionKey.OBSERVATION]
         if return_observations:
             all_observations.append(deepcopy(observation))
 
+        # TODO(azouitine): Move this in processor side
         observation = {
             key: observation[key].to(device, non_blocking=device.type == "cuda") for key in observation
         }
@@ -195,7 +209,9 @@ def rollout(
 
     # Track the final observation.
     if return_observations:
-        observation = preprocess_observation(observation)
+        transition = (observation, None, None, None, None, None, None)
+        processed_transition = obs_processor(transition)
+        observation = processed_transition[TransitionKey.OBSERVATION]
         all_observations.append(deepcopy(observation))
 
     # Stack the sequence along the first dimension so that we have (batch, sequence, *) tensors.
@@ -243,11 +259,7 @@ def eval_policy(
     if max_episodes_rendered > 0 and not videos_dir:
         raise ValueError("If max_episodes_rendered > 0, videos_dir must be provided.")
 
-    # Handle accelerate-wrapped models by unwrapping them
-    if hasattr(policy, 'module') and isinstance(policy.module, PreTrainedPolicy):
-        # This is likely an accelerate-wrapped model (DistributedDataParallel)
-        policy = policy.module
-    elif not isinstance(policy, PreTrainedPolicy):
+    if not isinstance(policy, PreTrainedPolicy):
         raise ValueError(
             f"Policy of type 'PreTrainedPolicy' is expected, but type '{type(policy)}' was provided."
         )
@@ -505,10 +517,6 @@ def eval_main(cfg: EvalPipelineConfig):
     logging.info("End of eval")
 
 
-def main():
+if __name__ == "__main__":
     init_logging()
     eval_main()
-
-
-if __name__ == "__main__":
-    main()

src/lerobot/scripts/rl/actor.py

@@ -62,8 +62,14 @@ from lerobot.configs import parser
 from lerobot.configs.train import TrainRLServerPipelineConfig
 from lerobot.policies.factory import make_policy
 from lerobot.policies.sac.modeling_sac import SACPolicy
+from lerobot.processor.pipeline import TransitionKey
 from lerobot.robots import so100_follower  # noqa: F401
-from lerobot.scripts.rl.gym_manipulator import make_robot_env
+from lerobot.scripts.rl.gym_manipulator import (
+    create_transition,
+    make_processors,
+    make_robot_env,
+    step_env_and_process_transition,
+)
 from lerobot.teleoperators import gamepad, so101_leader  # noqa: F401
 from lerobot.transport import services_pb2, services_pb2_grpc
 from lerobot.transport.utils import (
@@ -236,7 +242,8 @@ def act_with_policy(
 
     logging.info("make_env online")
 
-    online_env = make_robot_env(cfg=cfg.env)
+    online_env, teleop_device = make_robot_env(cfg=cfg.env)
+    env_processor, action_processor = make_processors(online_env, cfg.env)
 
     set_seed(cfg.seed)
     device = get_safe_torch_device(cfg.policy.device, log=True)
@@ -257,6 +264,13 @@ def act_with_policy(
     assert isinstance(policy, nn.Module)
 
     obs, info = online_env.reset()
+    complementary_data = {"raw_joint_positions": info.pop("raw_joint_positions")}
+    env_processor.reset()
+    action_processor.reset()
+
+    # Process initial observation
+    transition = create_transition(observation=obs, info=info, complementary_data=complementary_data)
+    transition = env_processor(transition)
 
     # NOTE: For the moment we will solely handle the case of a single environment
     sum_reward_episode = 0
@@ -274,45 +288,57 @@ def act_with_policy(
             logging.info("[ACTOR] Shutting down act_with_policy")
             return
 
-        if interaction_step >= cfg.policy.online_step_before_learning:
-            # Time policy inference and check if it meets FPS requirement
-            with policy_timer:
-                action = policy.select_action(batch=obs)
-            policy_fps = policy_timer.fps_last
+        observation = transition[TransitionKey.OBSERVATION]
 
-            log_policy_frequency_issue(policy_fps=policy_fps, cfg=cfg, interaction_step=interaction_step)
+        # Time policy inference and check if it meets FPS requirement
+        with policy_timer:
+            # Extract observation from transition for policy
+            action = policy.select_action(batch=observation)
+        policy_fps = policy_timer.fps_last
 
-        else:
-            action = online_env.action_space.sample()
+        log_policy_frequency_issue(policy_fps=policy_fps, cfg=cfg, interaction_step=interaction_step)
 
-        next_obs, reward, done, truncated, info = online_env.step(action)
+        # Use the new step function
+        new_transition, terminate_episode = step_env_and_process_transition(
+            env=online_env,
+            transition=transition,
+            action=action,
+            teleop_device=teleop_device,
+            env_processor=env_processor,
+            action_processor=action_processor,
+        )
+
+        # Extract values from processed transition
+        next_observation = new_transition[TransitionKey.OBSERVATION]
+        executed_action = new_transition[TransitionKey.COMPLEMENTARY_DATA]["teleop_action"]
+        reward = new_transition[TransitionKey.REWARD]
+        done = new_transition.get(TransitionKey.DONE, False)
+        truncated = new_transition.get(TransitionKey.TRUNCATED, False)
 
         sum_reward_episode += float(reward)
-        # Increment total steps counter for intervention rate
         episode_total_steps += 1
 
-        # NOTE: We override the action if the intervention is True, because the action applied is the intervention action
-        if "is_intervention" in info and info["is_intervention"]:
-            # NOTE: The action space for demonstration before hand is with the full action space
-            # but sometimes for example we want to deactivate the gripper
-            action = info["action_intervention"]
+        # Check for intervention from transition info
+        intervention_info = new_transition[TransitionKey.INFO]
+        if intervention_info.get("is_intervention", False):
             episode_intervention = True
-            # Increment intervention steps counter
             episode_intervention_steps += 1
 
+        # Create transition for learner (convert to old format)
         list_transition_to_send_to_learner.append(
             Transition(
-                state=obs,
-                action=action,
+                state=observation,
+                action=executed_action,
                 reward=reward,
-                next_state=next_obs,
+                next_state=next_observation,
                 done=done,
-                truncated=truncated,  # TODO: (azouitine) Handle truncation properly
-                complementary_info=info,
+                truncated=truncated,
+                complementary_info={},  # new_transition[TransitionKey.COMPLEMENTARY_DATA],
             )
         )
-        # assign obs to the next obs and continue the rollout
-        obs = next_obs
+
+        # Update transition for next iteration
+        transition = new_transition
 
         if done or truncated:
             logging.info(f"[ACTOR] Global step {interaction_step}: Episode reward: {sum_reward_episode}")
@@ -347,12 +373,21 @@ def act_with_policy(
                 )
             )
 
-            # Reset intervention counters
+            # Reset intervention counters and environment
             sum_reward_episode = 0.0
             episode_intervention = False
             episode_intervention_steps = 0
             episode_total_steps = 0
+
+            # Reset environment and processors
             obs, info = online_env.reset()
+            complementary_data = {"raw_joint_positions": info.pop("raw_joint_positions")}
+            env_processor.reset()
+            action_processor.reset()
+
+            # Process initial observation
+            transition = create_transition(observation=obs, info=info, complementary_data=complementary_data)
+            transition = env_processor(transition)
 
         if cfg.env.fps is not None:
             dt_time = time.perf_counter() - start_time

src/lerobot/scripts/server/robot_client.py

@@ -302,6 +302,11 @@ class RobotClient:
 
                     self.logger.debug(f"Current latest action: {latest_action}")
 
+                    # Get queue state before changes
+                    old_size, old_timesteps = self._inspect_action_queue()
+                    if not old_timesteps:
+                        old_timesteps = [latest_action]  # queue was empty
+
                     # Get queue state before changes
                     old_size, old_timesteps = self._inspect_action_queue()
                     if not old_timesteps:

src/lerobot/scripts/train.py

@@ -16,7 +16,6 @@
 import logging
 import time
 from contextlib import nullcontext
-from functools import partial
 from pprint import pformat
 from typing import Any
 
@@ -24,8 +23,6 @@ import torch
 from termcolor import colored
 from torch.amp import GradScaler
 from torch.optim import Optimizer
-import os
-from datetime import timedelta
 
 from lerobot.configs import parser
 from lerobot.configs.train import TrainPipelineConfig
@@ -55,8 +52,6 @@ from lerobot.utils.utils import (
 )
 from lerobot.utils.wandb_utils import WandBLogger
 
-def is_launched_with_accelerate() -> bool:
-    return "ACCELERATE_MIXED_PRECISION" in os.environ
 
 def update_policy(
     train_metrics: MetricsTracker,
@@ -64,65 +59,36 @@ def update_policy(
     batch: Any,
     optimizer: Optimizer,
     grad_clip_norm: float,
-    grad_scaler: GradScaler | None,
+    grad_scaler: GradScaler,
     lr_scheduler=None,
     use_amp: bool = False,
     lock=None,
-    accelerator=None,
 ) -> tuple[MetricsTracker, dict]:
     start_time = time.perf_counter()
     device = get_device_from_parameters(policy)
     policy.train()
-    
-    grad_norm = 0.0  # Initialize grad_norm to avoid undefined variable
-
-    if accelerator:
-        with accelerator.accumulate(policy):
-            with torch.autocast(device_type=device.type) if use_amp else nullcontext():
-                loss, output_dict = policy.forward(batch)
-            # TODO(rcadene): policy.unnormalize_outputs(out_dict)
-            accelerator.backward(loss)
-            if accelerator.sync_gradients:
-                grad_norm = torch.nn.utils.clip_grad_norm_(
-                    policy.parameters(),
-                    grad_clip_norm,
-                    error_if_nonfinite=False,
-                )
-            optimizer.step()
-            optimizer.zero_grad()
-    else:
-        # Standard training loop without accelerate
-        with torch.autocast(device_type=device.type) if use_amp else nullcontext():
-            loss, output_dict = policy.forward(batch)
+    with torch.autocast(device_type=device.type) if use_amp else nullcontext():
+        loss, output_dict = policy.forward(batch)
         # TODO(rcadene): policy.unnormalize_outputs(out_dict)
-        
-        if grad_scaler is not None:
-            grad_scaler.scale(loss).backward()
-            # Unscale the gradient of the optimizer's assigned params in-place **prior to gradient clipping**.
-            grad_scaler.unscale_(optimizer)
-            grad_norm = torch.nn.utils.clip_grad_norm_(
-                policy.parameters(),
-                grad_clip_norm,
-                error_if_nonfinite=False,
-            )
-            # Optimizer's gradients are already unscaled, so scaler.step does not unscale them,
-            # although it still skips optimizer.step() if the gradients contain infs or NaNs.
-            with lock if lock is not None else nullcontext():
-                grad_scaler.step(optimizer)
-            # Updates the scale for next iteration.
-            grad_scaler.update()
-        else:
-            # Without GradScaler (fallback)
-            loss.backward()
-            grad_norm = torch.nn.utils.clip_grad_norm_(
-                policy.parameters(),
-                grad_clip_norm,
-                error_if_nonfinite=False,
-            )
-            with lock if lock is not None else nullcontext():
-                optimizer.step()
+    grad_scaler.scale(loss).backward()
 
-        optimizer.zero_grad()
+    # Unscale the gradient of the optimizer's assigned params in-place **prior to gradient clipping**.
+    grad_scaler.unscale_(optimizer)
+
+    grad_norm = torch.nn.utils.clip_grad_norm_(
+        policy.parameters(),
+        grad_clip_norm,
+        error_if_nonfinite=False,
+    )
+
+    # Optimizer's gradients are already unscaled, so scaler.step does not unscale them,
+    # although it still skips optimizer.step() if the gradients contain infs or NaNs.
+    with lock if lock is not None else nullcontext():
+        grad_scaler.step(optimizer)
+    # Updates the scale for next iteration.
+    grad_scaler.update()
+
+    optimizer.zero_grad()
 
     # Step through pytorch scheduler at every batch instead of epoch
     if lr_scheduler is not None:
@@ -133,7 +99,7 @@ def update_policy(
         policy.update()
 
     train_metrics.loss = loss.item()
-    train_metrics.grad_norm = grad_norm.item() if isinstance(grad_norm, torch.Tensor) else grad_norm
+    train_metrics.grad_norm = grad_norm.item()
     train_metrics.lr = optimizer.param_groups[0]["lr"]
     train_metrics.update_s = time.perf_counter() - start_time
     return train_metrics, output_dict
@@ -142,33 +108,8 @@ def update_policy(
 @parser.wrap()
 def train(cfg: TrainPipelineConfig):
     cfg.validate()
-    
-    accelerator = None
-    if is_launched_with_accelerate():
-        import accelerate
-
-        # For example pi0 has unused params (last llm block)
-        from accelerate import DistributedDataParallelKwargs
-        ddp_kwargs = DistributedDataParallelKwargs(find_unused_parameters=True)
-        # accelerator = accelerate.Accelerator(step_scheduler_with_optimizer=False, kwargs_handlers=[ddp_kwargs])
-        from accelerate import InitProcessGroupKwargs
-        # Set NCCL timeout (default 30 minutes = 1800 seconds)
-        nccl_timeout = getattr(cfg, 'nccl_timeout', 1800)
-        ddp_init_kwargs = InitProcessGroupKwargs(timeout=timedelta(seconds=nccl_timeout)) # FIXME(mshukor): allow user to set timeout. This should be longer than the evaluation time
-        # Set gradient accumulation steps (default 1)
-        gradient_accumulation_steps = getattr(cfg, 'gradient_accumulation_steps', 1)
-        accelerator = accelerate.Accelerator(step_scheduler_with_optimizer=False, gradient_accumulation_steps=gradient_accumulation_steps, kwargs_handlers=[ddp_init_kwargs, ddp_kwargs])
-        if accelerator is not None and not accelerator.is_main_process:
-            # Disable duplicate logging on non-main processes
-            logging.info(f"Setting logging level on non-main process {accelerator.process_index} to WARNING.")
-            logging.getLogger().setLevel(logging.WARNING)
-
     logging.info(pformat(cfg.to_dict()))
 
-    if accelerator and not accelerator.is_main_process:
-            # Disable logging on non-main processes.
-            cfg.wandb.enable = False
-
     if cfg.wandb.enable and cfg.wandb.project:
         wandb_logger = WandBLogger(cfg)
     else:
@@ -202,8 +143,7 @@ def train(cfg: TrainPipelineConfig):
 
     logging.info("Creating optimizer and scheduler")
     optimizer, lr_scheduler = make_optimizer_and_scheduler(cfg, policy)
-    # Only use GradScaler when not using accelerate (accelerate handles mixed precision internally)
-    grad_scaler = None if accelerator else GradScaler(device.type, enabled=cfg.policy.use_amp)
+    grad_scaler = GradScaler(device.type, enabled=cfg.policy.use_amp)
 
     step = 0  # number of policy updates (forward + backward + optim)
 
@@ -245,11 +185,6 @@ def train(cfg: TrainPipelineConfig):
     )
     dl_iter = cycle(dataloader)
 
-    # Prepare models for accelerate if using multi-GPU
-    if accelerator:
-        policy, optimizer, dataloader = accelerator.prepare(policy, optimizer, dataloader)
-        dl_iter = cycle(dataloader)
-
     policy.train()
 
     train_metrics = {
@@ -270,10 +205,9 @@ def train(cfg: TrainPipelineConfig):
         batch = next(dl_iter)
         train_tracker.dataloading_s = time.perf_counter() - start_time
 
-        if not accelerator:
-            for key in batch:
-                if isinstance(batch[key], torch.Tensor):
-                    batch[key] = batch[key].to(device, non_blocking=device.type == "cuda")
+        for key in batch:
+            if isinstance(batch[key], torch.Tensor):
+                batch[key] = batch[key].to(device, non_blocking=device.type == "cuda")
 
         train_tracker, output_dict = update_policy(
             train_tracker,
@@ -284,7 +218,6 @@ def train(cfg: TrainPipelineConfig):
             grad_scaler=grad_scaler,
             lr_scheduler=lr_scheduler,
             use_amp=cfg.policy.use_amp,
-            accelerator=accelerator,
         )
 
         # Note: eval and checkpoint happens *after* the `step`th training update has completed, so we
@@ -304,17 +237,15 @@ def train(cfg: TrainPipelineConfig):
                 wandb_logger.log_dict(wandb_log_dict, step)
             train_tracker.reset_averages()
 
-        if cfg.save_checkpoint and is_saving_step and (not accelerator or accelerator.is_main_process):
+        if cfg.save_checkpoint and is_saving_step:
             logging.info(f"Checkpoint policy after step {step}")
             checkpoint_dir = get_step_checkpoint_dir(cfg.output_dir, cfg.steps, step)
-            # Unwrap model for accelerate
-            policy_to_save = accelerator.unwrap_model(policy) if accelerator else policy
-            save_checkpoint(checkpoint_dir, step, cfg, policy_to_save, optimizer, lr_scheduler)
+            save_checkpoint(checkpoint_dir, step, cfg, policy, optimizer, lr_scheduler)
             update_last_checkpoint(checkpoint_dir)
             if wandb_logger:
                 wandb_logger.log_policy(checkpoint_dir)
 
-        if cfg.env and is_eval_step and (not accelerator or accelerator.is_main_process):
+        if cfg.env and is_eval_step:
             step_id = get_step_identifier(step, cfg.steps)
             logging.info(f"Eval policy at step {step}")
             with (
@@ -323,7 +254,7 @@ def train(cfg: TrainPipelineConfig):
             ):
                 eval_info = eval_policy(
                     eval_env,
-                    accelerator.unwrap_model(policy) if accelerator else policy,
+                    policy,
                     cfg.eval.n_episodes,
                     videos_dir=cfg.output_dir / "eval" / f"videos_step_{step_id}",
                     max_episodes_rendered=4,
@@ -355,10 +286,6 @@ def train(cfg: TrainPipelineConfig):
         policy.push_model_to_hub(cfg)
 
 
-def main():
+if __name__ == "__main__":
     init_logging()
     train()
-
-
-if __name__ == "__main__":
-    main()

src/lerobot/setup_motors.py

@@ -18,7 +18,7 @@ Helper to set motor ids and baudrate.
 Example:
 
 ```shell
-lerobot-setup-motors \
+python -m lerobot.setup_motors \
     --teleop.type=so100_leader \
     --teleop.port=/dev/tty.usbmodem575E0031751
 ```
@@ -80,9 +80,5 @@ def setup_motors(cfg: SetupConfig):
     device.setup_motors()
 
 
-def main():
-    setup_motors()
-
-
 if __name__ == "__main__":
-    main()
+    setup_motors()

src/lerobot/teleoperate.py

@@ -18,7 +18,7 @@ Simple script to control a robot from teleoperation.
 Example:
 
 ```shell
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
     --robot.type=so101_follower \
     --robot.port=/dev/tty.usbmodem58760431541 \
     --robot.cameras="{ front: {type: opencv, index_or_path: 0, width: 1920, height: 1080, fps: 30}}" \
@@ -32,7 +32,7 @@ lerobot-teleoperate \
 Example teleoperation with bimanual so100:
 
 ```shell
-lerobot-teleoperate \
+python -m lerobot.teleoperate \
   --robot.type=bi_so100_follower \
   --robot.left_arm_port=/dev/tty.usbmodem5A460851411 \
   --robot.right_arm_port=/dev/tty.usbmodem5A460812391 \
@@ -153,9 +153,5 @@ def teleoperate(cfg: TeleoperateConfig):
         robot.disconnect()
 
 
-def main():
-    teleoperate()
-
-
 if __name__ == "__main__":
-    main()
+    teleoperate()

src/lerobot/teleoperators/gamepad/teleop_gamepad.py

@@ -107,6 +107,45 @@ class GamepadTeleop(Teleoperator):
 
         return action_dict
 
+    def get_teleop_events(self) -> dict[str, Any]:
+        """
+        Get extra control events from the gamepad such as intervention status,
+        episode termination, success indicators, etc.
+
+        Returns:
+            Dictionary containing:
+                - is_intervention: bool - Whether human is currently intervening
+                - terminate_episode: bool - Whether to terminate the current episode
+                - success: bool - Whether the episode was successful
+                - rerecord_episode: bool - Whether to rerecord the episode
+        """
+        if self.gamepad is None:
+            return {
+                "is_intervention": False,
+                "terminate_episode": False,
+                "success": False,
+                "rerecord_episode": False,
+            }
+
+        # Update gamepad state to get fresh inputs
+        self.gamepad.update()
+
+        # Check if intervention is active
+        is_intervention = self.gamepad.should_intervene()
+
+        # Get episode end status
+        episode_end_status = self.gamepad.get_episode_end_status()
+        terminate_episode = episode_end_status is not None
+        success = episode_end_status == "success"
+        rerecord_episode = episode_end_status == "rerecord_episode"
+
+        return {
+            "is_intervention": is_intervention,
+            "terminate_episode": terminate_episode,
+            "success": success,
+            "rerecord_episode": rerecord_episode,
+        }
+
     def disconnect(self) -> None:
         """Disconnect from the gamepad."""
         if self.gamepad is not None:

src/lerobot/teleoperators/keyboard/teleop_keyboard.py

@@ -235,3 +235,67 @@ class KeyboardEndEffectorTeleop(KeyboardTeleop):
             action_dict["gripper"] = gripper_action
 
         return action_dict
+
+    def get_teleop_events(self) -> dict[str, Any]:
+        """
+        Get extra control events from the keyboard such as intervention status,
+        episode termination, success indicators, etc.
+
+        Keyboard mappings:
+        - Any movement keys pressed = intervention active
+        - 's' key = success (terminate episode successfully)
+        - 'r' key = rerecord episode (terminate and rerecord)
+        - 'q' key = quit episode (terminate without success)
+
+        Returns:
+            Dictionary containing:
+                - is_intervention: bool - Whether human is currently intervening
+                - terminate_episode: bool - Whether to terminate the current episode
+                - success: bool - Whether the episode was successful
+                - rerecord_episode: bool - Whether to rerecord the episode
+        """
+        if not self.is_connected:
+            return {
+                "is_intervention": False,
+                "terminate_episode": False,
+                "success": False,
+                "rerecord_episode": False,
+            }
+
+        # Check if any movement keys are currently pressed (indicates intervention)
+        movement_keys = [
+            keyboard.Key.up,
+            keyboard.Key.down,
+            keyboard.Key.left,
+            keyboard.Key.right,
+            keyboard.Key.shift,
+            keyboard.Key.shift_r,
+            keyboard.Key.ctrl_r,
+            keyboard.Key.ctrl_l,
+        ]
+        is_intervention = any(self.current_pressed.get(key, False) for key in movement_keys)
+
+        # Check for episode control commands from misc_keys_queue
+        terminate_episode = False
+        success = False
+        rerecord_episode = False
+
+        # Process any pending misc keys
+        while not self.misc_keys_queue.empty():
+            key = self.misc_keys_queue.get_nowait()
+            if key == "s":
+                terminate_episode = True
+                success = True
+            elif key == "r":
+                terminate_episode = True
+                rerecord_episode = True
+            elif key == "q":
+                terminate_episode = True
+                success = False
+
+        return {
+            "is_intervention": is_intervention,
+            "terminate_episode": terminate_episode,
+            "success": success,
+            "rerecord_episode": rerecord_episode,
+        }

src/lerobot/teleoperators/teleoperator.py

@@ -160,6 +160,18 @@ class Teleoperator(abc.ABC):
         """
         pass
 
+    @abc.abstractmethod
+    def get_teleop_events(self) -> dict[str, Any]:
+        """
+        Get extra control events from the teleoperator such as intervention status,
+        episode termination, success indicators, etc.
+        Check the implementation of the gamepad for an example.
+
+        Returns:
+            dict[str, Any]: A dictionary containing control events with keys and values that are specific to the setup.
+        """
+        pass
+
     @abc.abstractmethod
     def send_feedback(self, feedback: dict[str, Any]) -> None:
         """

src/lerobot/templates/lerobot_modelcard_template.md

@@ -44,7 +44,7 @@ Below is the short version on how to train and run inference/eval:
 ### Train from scratch
 
 ```bash
-lerobot-train \
+python -m lerobot.scripts.train \
   --dataset.repo_id=${HF_USER}/<dataset> \
   --policy.type=act \
   --output_dir=outputs/train/<desired_policy_repo_id> \
@@ -59,7 +59,7 @@ _Writes checkpoints to `outputs/train/<desired_policy_repo_id>/checkpoints/`._
 ### Evaluate the policy/run inference
 
 ```bash
-lerobot-record \
+python -m lerobot.record \
   --robot.type=so100_follower \
   --dataset.repo_id=<hf_user>/eval_<dataset> \
   --policy.path=<hf_user>/<desired_policy_repo_id> \

src/lerobot/templates/robotprocessor_modelcard_template.md

@@ -0,0 +1,195 @@
+---
+library_name: lerobot
+tags:
+  - robotics
+  - lerobot
+  - safetensors
+pipeline_tag: robotics
+---
+
+# RobotProcessor
+
+## Overview
+
+RobotProcessor is a composable, debuggable post-processing pipeline for robot transitions in the LeRobot framework. It orchestrates an ordered collection of small, functional transforms (steps) that are executed left-to-right on each incoming `EnvTransition`.
+
+## Architecture
+
+The RobotProcessor provides a modular architecture for processing robot environment transitions through a sequence of composable steps. Each step is a callable that accepts a full `EnvTransition` tuple and returns a potentially modified tuple of the same structure.
+
+### EnvTransition Structure
+
+An `EnvTransition` is a 7-tuple containing:
+
+1. **observation**: Current state observation
+2. **action**: Action taken (can be None)
+3. **reward**: Reward received (float or None)
+4. **done**: Episode termination flag (bool or None)
+5. **truncated**: Episode truncation flag (bool or None)
+6. **info**: Additional information dictionary
+7. **complementary_data**: Extra data dictionary
+
+## Key Features
+
+- **Composable Pipeline**: Chain multiple processing steps in a specific order
+- **State Persistence**: Save and load processor state using SafeTensors format
+- **Hugging Face Hub Integration**: Easy sharing and loading via `save_pretrained()` and `from_pretrained()`
+- **Debugging Support**: Step-through functionality to inspect intermediate transformations
+- **Hook System**: Before/after step hooks for additional processing or monitoring
+- **Device Support**: Move tensor states to different devices (CPU/GPU)
+- **Performance Profiling**: Built-in profiling to identify bottlenecks
+
+## Installation
+
+Follow the [installation instructions](https://huggingface.co/docs/lerobot/installation) to install the package.
+
+## Usage
+
+### Basic Example
+
+```python
+from lerobot.processor.pipeline import RobotProcessor
+from your_steps import ObservationNormalizer, VelocityCalculator
+
+# Create a processor with multiple steps
+processor = RobotProcessor(
+    steps=[
+        ObservationNormalizer(mean=0, std=1),
+        VelocityCalculator(window_size=5),
+    ],
+    name="my_robot_processor",
+    seed=42
+)
+
+# Process a transition
+obs, info = env.reset()
+transition = (obs, None, 0.0, False, False, info, {})
+processed_transition = processor(transition)
+
+# Extract processed observation
+processed_obs = processed_transition[0]
+```
+
+### Saving and Loading
+
+```python
+# Save locally
+processor.save_pretrained("./my_processor")
+
+# Push to Hugging Face Hub
+processor.push_to_hub("username/my-robot-processor")
+
+# Load from Hub
+loaded_processor = RobotProcessor.from_pretrained("username/my-robot-processor")
+```
+
+### Debugging with Step-Through
+
+```python
+# Inspect intermediate results
+for idx, intermediate_transition in enumerate(processor.step_through(transition)):
+    print(f"After step {idx}: {intermediate_transition[0]}")  # Print observation
+```
+
+### Using Hooks
+
+```python
+# Add monitoring hook
+def log_observation(step_idx, transition):
+    print(f"Step {step_idx}: obs shape = {transition[0].shape}")
+    return None  # Don't modify transition
+
+processor.register_before_step_hook(log_observation)
+```
+
+## Creating Custom Steps
+
+To create a custom processor step, implement the `ProcessorStep` protocol:
+
+```python
+from lerobot.processor.pipeline import ProcessorStepRegistry, EnvTransition
+
+@ProcessorStepRegistry.register("my_custom_step")
+class MyCustomStep:
+    def __init__(self, param1=1.0):
+        self.param1 = param1
+        self.buffer = []
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        obs, action, reward, done, truncated, info, comp_data = transition
+        # Process observation
+        processed_obs = obs * self.param1
+        return (processed_obs, action, reward, done, truncated, info, comp_data)
+
+    def get_config(self) -> dict:
+        return {"param1": self.param1}
+
+    def state_dict(self) -> dict:
+        # Return only torch.Tensor state
+        return {}
+
+    def load_state_dict(self, state: dict) -> None:
+        # Load tensor state
+        pass
+
+    def reset(self) -> None:
+        # Clear buffers at episode boundaries
+        self.buffer.clear()
+```
+
+## Advanced Features
+
+### Device Management
+
+```python
+# Move all tensor states to GPU
+processor = processor.to("cuda")
+
+# Move to specific device
+processor = processor.to(torch.device("cuda:1"))
+```
+
+### Performance Profiling
+
+```python
+# Profile step execution times
+profile_results = processor.profile_steps(transition, num_runs=100)
+for step_name, time_ms in profile_results.items():
+    print(f"{step_name}: {time_ms:.3f} ms")
+```
+
+### Processor Slicing
+
+```python
+# Get a single step
+first_step = processor[0]
+
+# Create a sub-processor with steps 1-3
+sub_processor = processor[1:4]
+```
+
+## Model Card Specifications
+
+- **Pipeline Tag**: robotics
+- **Library**: lerobot
+- **Format**: safetensors
+- **License**: Apache 2.0
+
+## Limitations
+
+- Steps must maintain the 7-tuple structure of EnvTransition
+- All tensor state must be separated from configuration for proper serialization
+- Steps are executed sequentially (no parallel processing within a single transition)
+
+## Citation
+
+If you use RobotProcessor in your research, please cite:
+
+```bibtex
+@misc{cadene2024lerobot,
+    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascale, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
+    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
+    howpublished = "\url{https://github.com/huggingface/lerobot}",
+    year = {2024}
+}
+```

src/lerobot/utils/robot_utils.py

@@ -17,9 +17,10 @@ import time
 
 
 def busy_wait(seconds):
-    if platform.system() == "Darwin" or platform.system() == "Windows":
-        # On Mac and Windows, `time.sleep` is not accurate and we need to use this while loop trick,
+    if platform.system() == "Darwin":
+        # On Mac, `time.sleep` is not accurate and we need to use this while loop trick,
         # but it consumes CPU cycles.
+        # TODO(rcadene): find an alternative: from python 11, time.sleep is precise
         end_time = time.perf_counter() + seconds
         while time.perf_counter() < end_time:
             pass

src/lerobot/utils/train_utils.py

@@ -60,39 +60,11 @@ def load_training_step(save_dir: Path) -> int:
 
 
 def update_last_checkpoint(checkpoint_dir: Path) -> Path:
-    import fcntl
-    import tempfile
-    import os
-    
     last_checkpoint_dir = checkpoint_dir.parent / LAST_CHECKPOINT_LINK
+    if last_checkpoint_dir.is_symlink():
+        last_checkpoint_dir.unlink()
     relative_target = checkpoint_dir.relative_to(checkpoint_dir.parent)
-    
-    # Use file locking to prevent race conditions in multi-GPU training
-    lock_file = checkpoint_dir.parent / ".symlink_lock"
-    
-    try:
-        with open(lock_file, 'w') as f:
-            # Get exclusive lock
-            fcntl.flock(f.fileno(), fcntl.LOCK_EX)
-            
-            # Update symlink atomically
-            if last_checkpoint_dir.exists() or last_checkpoint_dir.is_symlink():
-                last_checkpoint_dir.unlink()
-            last_checkpoint_dir.symlink_to(relative_target)
-            
-    except (OSError, FileExistsError) as e:
-        # Handle race conditions gracefully - another process may have already updated
-        if not last_checkpoint_dir.exists():
-            try:
-                last_checkpoint_dir.symlink_to(relative_target)
-            except FileExistsError:
-                pass  # Another process created it, that's fine
-    finally:
-        # Clean up lock file
-        try:
-            lock_file.unlink()
-        except FileNotFoundError:
-            pass
+    last_checkpoint_dir.symlink_to(relative_target)
 
 
 def save_checkpoint(

test_accelerate_1gpu_local.sh

@@ -1,45 +0,0 @@
-#!/bin/bash
-
-echo "=== Local 1-GPU Accelerate Training Test with SmolVLA ==="
-echo "Environment: multi"
-echo "GPU: 1"
-echo "Steps: 50 (quick local test)"
-echo ""
-
-# Activate conda environment
-source /fsx/dana_aubakirova/miniconda3/etc/profile.d/conda.sh
-conda activate multi
-
-# Set CUDA environment for 1 GPU
-export CUDA_VISIBLE_DEVICES=0
-export PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128,expandable_segments:True
-export TORCH_DISTRIBUTED_DEBUG=OFF
-export CUDA_LAUNCH_BLOCKING=0
-export TRANSFORMERS_NO_ADVISORY_WARNINGS=1
-
-# Change to working directory
-cd /fsx/dana_aubakirova/vla/pr/lerobot
-
-# Set output directory with timestamp
-export OUTPUT_DIR="outputs/test_accelerate_1gpu_local_$(date +%Y%m%d_%H%M%S)"
-
-echo "Output directory: $OUTPUT_DIR"
-echo ""
-
-# Test accelerate training with 1 GPU
-accelerate launch --config_file accelerate_configs/1gpu_config.yaml -m lerobot.scripts.train \
-    --policy.path=lerobot/smolvla_base \
-    --policy.push_to_hub=false \
-    --dataset.repo_id=lerobot/svla_so100_sorting \
-    --dataset.video_backend=pyav \
-    --steps=50 \
-    --save_freq=25 \
-    --log_freq=5 \
-    --batch_size=1 \
-    --num_workers=0 \
-    --output_dir=$OUTPUT_DIR \
-    --wandb.enable=false
-
-echo ""
-echo "=== Training completed! ==="
-echo "Check outputs in: $OUTPUT_DIR"

test_accelerate_2gpu.slurm

@@ -1,67 +0,0 @@
-#!/bin/bash
-#SBATCH --job-name=test_accelerate
-#SBATCH --nodes=1
-#SBATCH --ntasks-per-node=1
-#SBATCH --cpus-per-task=16
-#SBATCH --gres=gpu:2
-#SBATCH --time=1:00:00
-#SBATCH --partition=hopper-prod
-#SBATCH --output=/fsx/dana_aubakirova/vla/logs/test_accelerate_%j.out
-#SBATCH --error=/fsx/dana_aubakirova/vla/logs/test_accelerate_%j.err
-
-# Create logs directory if it doesn't exist
-mkdir -p /fsx/dana_aubakirova/vla/pr/lerobot/logs
-
-# Activate conda environment
-source /fsx/dana_aubakirova/miniconda3/etc/profile.d/conda.sh
-conda activate multi
-
-# 2-GPU Test CUDA environment
-export CUDA_VISIBLE_DEVICES=0,1
-export PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128,expandable_segments:True
-export TORCH_DISTRIBUTED_DEBUG=OFF
-export NCCL_DEBUG=INFO
-export CUDA_LAUNCH_BLOCKING=0
-export ACCELERATE_USE_FSDP=false
-export ACCELERATE_USE_DEEPSPEED=false
-export HF_ACCELERATE_DEVICE_MAP=false
-export TRANSFORMERS_NO_ADVISORY_WARNINGS=1
-export SAFETENSORS_FAST_GPU=1
-export HF_HUB_ENABLE_HF_TRANSFER=1
-export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
-export ACCELERATE_TORCH_DEVICE_MAP_AUTO=false
-
-# Change to working directory
-cd /fsx/dana_aubakirova/vla/pr/lerobot
-
-echo "=== Testing Accelerate Multi-GPU Training with SmolVLA ==="
-echo "Dataset: lerobot/svla_so100_sorting"
-echo "GPUs: 2"
-echo "Steps: 100 (for quick test)"
-echo "Job ID: $SLURM_JOB_ID"
-echo ""
-
-# Set output directory with job ID
-export OUTPUT_DIR="outputs/test_accelerate_2gpu_job_${SLURM_JOB_ID}"
-
-echo "Output directory: $OUTPUT_DIR"
-echo ""
-
-# Test accelerate training
-accelerate launch --config_file accelerate_configs/2gpu_config_safe.yaml -m lerobot.scripts.train \
-    --policy.type=smolvla \
-    --policy.push_to_hub=false \
-    --dataset.repo_id=lerobot/svla_so100_sorting \
-    --dataset.video_backend=pyav \
-    --steps=100 \
-    --save_freq=50 \
-    --log_freq=5 \
-    --batch_size=2 \
-    --num_workers=0 \
-    --output_dir=$OUTPUT_DIR \
-    --wandb.enable=false
-
-echo ""
-echo "=== Training completed! ==="
-echo "Check logs and outputs in: $OUTPUT_DIR"
-echo "Job ID: $SLURM_JOB_ID"

test_direct_1gpu_local.sh

@@ -1,45 +0,0 @@
-#!/bin/bash
-
-echo "=== Direct 1-GPU Training Test with SmolVLA (no accelerate) ==="
-echo "Environment: multi"
-echo "GPU: 1"
-echo "Steps: 50 (quick local test)"
-echo ""
-
-# Activate conda environment
-source /fsx/dana_aubakirova/miniconda3/etc/profile.d/conda.sh
-conda activate multi
-
-# Set CUDA environment for 1 GPU
-export CUDA_VISIBLE_DEVICES=0
-export PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128,expandable_segments:True
-export TORCH_DISTRIBUTED_DEBUG=OFF
-export CUDA_LAUNCH_BLOCKING=0
-export TRANSFORMERS_NO_ADVISORY_WARNINGS=1
-
-# Change to working directory
-cd /fsx/dana_aubakirova/vla/pr/lerobot
-
-# Set output directory with timestamp
-export OUTPUT_DIR="outputs/test_direct_1gpu_local_$(date +%Y%m%d_%H%M%S)"
-
-echo "Output directory: $OUTPUT_DIR"
-echo ""
-
-# Test direct training with 1 GPU (no accelerate)
-python -m lerobot.scripts.train \
-    --policy.path=lerobot/smolvla_base \
-    --policy.push_to_hub=false \
-    --dataset.repo_id=lerobot/svla_so100_sorting \
-    --dataset.video_backend=pyav \
-    --steps=50 \
-    --save_freq=25 \
-    --log_freq=5 \
-    --batch_size=1 \
-    --num_workers=0 \
-    --output_dir=$OUTPUT_DIR \
-    --wandb.enable=false
-
-echo ""
-echo "=== Training completed! ==="
-echo "Check outputs in: $OUTPUT_DIR"

tests/envs/test_envs.py

@@ -22,7 +22,7 @@ from gymnasium.utils.env_checker import check_env
 
 import lerobot
 from lerobot.envs.factory import make_env, make_env_config
-from lerobot.envs.utils import preprocess_observation
+from lerobot.processor import RobotProcessor, TransitionKey, VanillaObservationProcessor
 from tests.utils import require_env
 
 OBS_TYPES = ["state", "pixels", "pixels_agent_pos"]
@@ -48,7 +48,12 @@ def test_factory(env_name):
     cfg = make_env_config(env_name)
     env = make_env(cfg, n_envs=1)
     obs, _ = env.reset()
-    obs = preprocess_observation(obs)
+
+    # Process observation using processor
+    obs_processor = RobotProcessor([VanillaObservationProcessor()])
+    transition = (obs, None, None, None, None, None, None)
+    processed_transition = obs_processor(transition)
+    obs = processed_transition[TransitionKey.OBSERVATION]
 
     # test image keys are float32 in range [0,1]
     for key in obs:

tests/policies/test_policies.py

@@ -27,13 +27,10 @@ from lerobot import available_policies
 from lerobot.configs.default import DatasetConfig
 from lerobot.configs.train import TrainPipelineConfig
 from lerobot.configs.types import FeatureType, NormalizationMode, PolicyFeature
-from lerobot.constants import ACTION, OBS_STATE
 from lerobot.datasets.factory import make_dataset
 from lerobot.datasets.utils import cycle, dataset_to_policy_features
 from lerobot.envs.factory import make_env, make_env_config
-from lerobot.envs.utils import preprocess_observation
 from lerobot.optim.factory import make_optimizer_and_scheduler
-from lerobot.policies.act.configuration_act import ACTConfig
 from lerobot.policies.act.modeling_act import ACTTemporalEnsembler
 from lerobot.policies.factory import (
     get_policy_class,
@@ -42,6 +39,7 @@ from lerobot.policies.factory import (
 )
 from lerobot.policies.normalize import Normalize, Unnormalize
 from lerobot.policies.pretrained import PreTrainedPolicy
+from lerobot.processor import RobotProcessor, TransitionKey, VanillaObservationProcessor
 from lerobot.utils.random_utils import seeded_context
 from tests.artifacts.policies.save_policy_to_safetensors import get_policy_stats
 from tests.utils import DEVICE, require_cpu, require_env, require_x86_64_kernel
@@ -187,7 +185,10 @@ def test_policy(ds_repo_id, env_name, env_kwargs, policy_name, policy_kwargs):
     observation, _ = env.reset(seed=train_cfg.seed)
 
     # apply transform to normalize the observations
-    observation = preprocess_observation(observation)
+    obs_processor = RobotProcessor([VanillaObservationProcessor()])
+    transition = (observation, None, None, None, None, None, None)
+    processed_transition = obs_processor(transition)
+    observation = processed_transition[TransitionKey.OBSERVATION]
 
     # send observation to device/gpu
     observation = {key: observation[key].to(DEVICE, non_blocking=True) for key in observation}
@@ -365,54 +366,6 @@ def test_normalize(insert_temporal_dim):
     unnormalize(output_batch)
 
 
-@pytest.mark.parametrize("multikey", [True, False])
-def test_multikey_construction(multikey: bool):
-    """
-    Asserts that multiple keys with type State/Action are correctly processed by the policy constructor,
-    preventing erroneous creation of the policy object.
-    """
-    input_features = {
-        "observation.state": PolicyFeature(
-            type=FeatureType.STATE,
-            shape=(10,),
-        ),
-    }
-    output_features = {
-        "action": PolicyFeature(
-            type=FeatureType.ACTION,
-            shape=(5,),
-        ),
-    }
-
-    if multikey:
-        """Simulates the complete state/action is constructed from more granular multiple
-        keys, of the same type as the overall state/action"""
-        input_features = {}
-        input_features["observation.state.subset1"] = PolicyFeature(type=FeatureType.STATE, shape=(5,))
-        input_features["observation.state.subset2"] = PolicyFeature(type=FeatureType.STATE, shape=(5,))
-        input_features["observation.state"] = PolicyFeature(type=FeatureType.STATE, shape=(10,))
-
-        output_features = {}
-        output_features["action.first_three_motors"] = PolicyFeature(type=FeatureType.ACTION, shape=(3,))
-        output_features["action.last_two_motors"] = PolicyFeature(type=FeatureType.ACTION, shape=(2,))
-        output_features["action"] = PolicyFeature(
-            type=FeatureType.ACTION,
-            shape=(5,),
-        )
-
-    config = ACTConfig(input_features=input_features, output_features=output_features)
-
-    state_condition = config.robot_state_feature == input_features[OBS_STATE]
-    action_condition = config.action_feature == output_features[ACTION]
-
-    assert state_condition, (
-        f"Discrepancy detected. Robot state feature is {config.robot_state_feature} but policy expects {input_features[OBS_STATE]}"
-    )
-    assert action_condition, (
-        f"Discrepancy detected. Action feature is {config.action_feature} but policy expects {output_features[ACTION]}"
-    )
-
-
 @pytest.mark.parametrize(
     "ds_repo_id, policy_name, policy_kwargs, file_name_extra",
     [

tests/processor/test_observation_processor.py

@@ -20,7 +20,11 @@ import torch
 
 from lerobot.configs.types import FeatureType
 from lerobot.constants import OBS_ENV_STATE, OBS_IMAGE, OBS_IMAGES, OBS_STATE
-from lerobot.processor import VanillaObservationProcessor
+from lerobot.processor import (
+    ImageProcessor,
+    StateProcessor,
+    VanillaObservationProcessor,
+)
 from lerobot.processor.pipeline import TransitionKey
 from tests.conftest import assert_contract_is_typed
 
@@ -42,7 +46,7 @@ def create_transition(
 
 def test_process_single_image():
     """Test processing a single image."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Create a mock image (H, W, C) format, uint8
     image = np.random.randint(0, 256, size=(64, 64, 3), dtype=np.uint8)
@@ -68,7 +72,7 @@ def test_process_single_image():
 
 def test_process_image_dict():
     """Test processing multiple images in a dictionary."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Create mock images
     image1 = np.random.randint(0, 256, size=(32, 32, 3), dtype=np.uint8)
@@ -91,7 +95,7 @@ def test_process_image_dict():
 
 def test_process_batched_image():
     """Test processing already batched images."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Create a batched image (B, H, W, C)
     image = np.random.randint(0, 256, size=(2, 64, 64, 3), dtype=np.uint8)
@@ -108,7 +112,7 @@ def test_process_batched_image():
 
 def test_invalid_image_format():
     """Test error handling for invalid image formats."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Test wrong channel order (channels first)
     image = np.random.randint(0, 256, size=(3, 64, 64), dtype=np.uint8)
@@ -121,7 +125,7 @@ def test_invalid_image_format():
 
 def test_invalid_image_dtype():
     """Test error handling for invalid image dtype."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Test wrong dtype
     image = np.random.rand(64, 64, 3).astype(np.float32)
@@ -134,7 +138,7 @@ def test_invalid_image_dtype():
 
 def test_no_pixels_in_observation():
     """Test processor when no pixels are in observation."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     observation = {"other_data": np.array([1, 2, 3])}
     transition = create_transition(observation=observation)
@@ -149,7 +153,7 @@ def test_no_pixels_in_observation():
 
 def test_none_observation():
     """Test processor with None observation."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     transition = create_transition()
     result = processor(transition)
@@ -159,7 +163,7 @@ def test_none_observation():
 
 def test_serialization_methods():
     """Test serialization methods."""
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
 
     # Test get_config
     config = processor.get_config()
@@ -178,7 +182,7 @@ def test_serialization_methods():
 
 def test_process_environment_state():
     """Test processing environment_state."""
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
 
     env_state = np.array([1.0, 2.0, 3.0], dtype=np.float32)
     observation = {"environment_state": env_state}
@@ -199,7 +203,7 @@ def test_process_environment_state():
 
 def test_process_agent_pos():
     """Test processing agent_pos."""
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
 
     agent_pos = np.array([0.5, -0.5, 1.0], dtype=np.float32)
     observation = {"agent_pos": agent_pos}
@@ -220,7 +224,7 @@ def test_process_agent_pos():
 
 def test_process_batched_states():
     """Test processing already batched states."""
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
 
     env_state = np.array([[1.0, 2.0], [3.0, 4.0]], dtype=np.float32)
     agent_pos = np.array([[0.5, -0.5], [1.0, -1.0]], dtype=np.float32)
@@ -238,7 +242,7 @@ def test_process_batched_states():
 
 def test_process_both_states():
     """Test processing both environment_state and agent_pos."""
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
 
     env_state = np.array([1.0, 2.0], dtype=np.float32)
     agent_pos = np.array([0.5, -0.5], dtype=np.float32)
@@ -263,7 +267,7 @@ def test_process_both_states():
 
 def test_no_states_in_observation():
     """Test processor when no states are in observation."""
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
 
     observation = {"other_data": np.array([1, 2, 3])}
     transition = create_transition(observation=observation)
@@ -355,6 +359,17 @@ def test_empty_observation():
     assert processed_obs == {}
 
 
+def test_custom_sub_processors():
+    """Test ObservationProcessor with custom sub-processors."""
+    image_proc = ImageProcessor()
+    state_proc = StateProcessor()
+    processor = VanillaObservationProcessor(image_processor=image_proc, state_processor=state_proc)
+
+    # Should use the provided processors
+    assert processor.image_processor is image_proc
+    assert processor.state_processor is state_proc
+
+
 def test_equivalent_to_original_function():
     """Test that ObservationProcessor produces equivalent results to preprocess_observation."""
     # Import the original function for comparison
@@ -411,7 +426,7 @@ def test_equivalent_with_image_dict():
 
 
 def test_image_processor_feature_contract_pixels_to_image(policy_feature_factory):
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
     features = {
         "pixels": policy_feature_factory(FeatureType.VISUAL, (3, 64, 64)),
         "keep": policy_feature_factory(FeatureType.ENV, (1,)),
@@ -425,7 +440,7 @@ def test_image_processor_feature_contract_pixels_to_image(policy_feature_factory
 
 
 def test_image_processor_feature_contract_observation_pixels_to_image(policy_feature_factory):
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
     features = {
         "observation.pixels": policy_feature_factory(FeatureType.VISUAL, (3, 64, 64)),
         "keep": policy_feature_factory(FeatureType.ENV, (1,)),
@@ -439,7 +454,7 @@ def test_image_processor_feature_contract_observation_pixels_to_image(policy_fea
 
 
 def test_image_processor_feature_contract_multi_camera_and_prefixed(policy_feature_factory):
-    processor = VanillaObservationProcessor()
+    processor = ImageProcessor()
     features = {
         "pixels.front": policy_feature_factory(FeatureType.VISUAL, (3, 64, 64)),
         "pixels.wrist": policy_feature_factory(FeatureType.VISUAL, (3, 64, 64)),
@@ -457,7 +472,7 @@ def test_image_processor_feature_contract_multi_camera_and_prefixed(policy_featu
 
 
 def test_state_processor_feature_contract_environment_and_agent_pos(policy_feature_factory):
-    processor = VanillaObservationProcessor()
+    processor = StateProcessor()
     features = {
         "environment_state": policy_feature_factory(FeatureType.STATE, (3,)),
         "agent_pos": policy_feature_factory(FeatureType.STATE, (7,)),
@@ -473,7 +488,7 @@ def test_state_processor_feature_contract_environment_and_agent_pos(policy_featu
 
 
 def test_state_processor_feature_contract_prefixed_inputs(policy_feature_factory):
-    proc = VanillaObservationProcessor()
+    proc = StateProcessor()
     features = {
         "observation.environment_state": policy_feature_factory(FeatureType.STATE, (2,)),
         "observation.agent_pos": policy_feature_factory(FeatureType.STATE, (4,)),

tests/processor/test_pipeline.py

@@ -21,6 +21,7 @@ from dataclasses import dataclass
 from pathlib import Path
 from typing import Any
 
+import numpy as np
 import pytest
 import torch
 import torch.nn as nn
@@ -267,25 +268,14 @@ def test_step_through_with_dict():
 
     assert len(results) == 3  # Original + 2 steps
 
-    # Ensure all results are EnvTransition dicts (regardless of input format)
+    # Ensure all results are dicts (same format as input)
     for result in results:
         assert isinstance(result, dict)
-        # Check that keys are TransitionKey enums or at least valid transition keys
-        for key in result:
-            assert key in [
-                TransitionKey.OBSERVATION,
-                TransitionKey.ACTION,
-                TransitionKey.REWARD,
-                TransitionKey.DONE,
-                TransitionKey.TRUNCATED,
-                TransitionKey.INFO,
-                TransitionKey.COMPLEMENTARY_DATA,
-            ]
 
-    # Check that the processing worked - verify step counters in complementary_data
-    assert results[1].get(TransitionKey.COMPLEMENTARY_DATA, {}).get("step1_counter") == 0
-    assert results[2].get(TransitionKey.COMPLEMENTARY_DATA, {}).get("step1_counter") == 0
-    assert results[2].get(TransitionKey.COMPLEMENTARY_DATA, {}).get("step2_counter") == 0
+    # Check that the processing worked - the complementary data from steps
+    # should show up in the info or complementary_data fields when converted back to dict
+    # Note: This depends on how _default_transition_to_batch handles complementary_data
+    # For now, just check that we get dict outputs
 
 
 def test_step_through_no_hooks():
@@ -363,6 +353,32 @@ def test_hooks():
     assert after_calls == [0]
 
 
+def test_reset():
+    """Test pipeline reset functionality."""
+    step = MockStep("test_step")
+    pipeline = RobotProcessor([step])
+
+    reset_called = []
+
+    def reset_hook():
+        reset_called.append(True)
+
+    pipeline.register_reset_hook(reset_hook)
+
+    # Make some calls to increment counter
+    transition = create_transition()
+    pipeline(transition)
+    pipeline(transition)
+
+    assert step.counter == 2
+
+    # Reset should reset step and call hook
+    pipeline.reset()
+
+    assert step.counter == 0
+    assert len(reset_called) == 1
+
+
 def test_unregister_hooks():
     """Test unregistering hooks from the pipeline."""
     step = MockStep("test_step")
@@ -402,6 +418,21 @@ def test_unregister_hooks():
     pipeline(transition)
     assert len(after_calls) == 0
 
+    # Test reset_hook
+    reset_calls = []
+
+    def reset_hook():
+        reset_calls.append(True)
+
+    pipeline.register_reset_hook(reset_hook)
+    pipeline.reset()
+    assert len(reset_calls) == 1
+
+    pipeline.unregister_reset_hook(reset_hook)
+    reset_calls.clear()
+    pipeline.reset()
+    assert len(reset_calls) == 0
+
 
 def test_unregister_nonexistent_hook():
     """Test error handling when unregistering hooks that don't exist."""
@@ -420,6 +451,9 @@ def test_unregister_nonexistent_hook():
     with pytest.raises(ValueError, match="not found in after_step_hooks"):
         pipeline.unregister_after_step_hook(some_hook)
 
+    with pytest.raises(ValueError, match="not found in reset_hooks"):
+        pipeline.unregister_reset_hook(reset_hook)
+
 
 def test_multiple_hooks_and_selective_unregister():
     """Test registering multiple hooks and selectively unregistering them."""
@@ -508,6 +542,22 @@ def test_hook_execution_order_documentation():
     assert execution_order == ["A", "C", "B"]  # B is now last
 
 
+def test_profile_steps():
+    """Test step profiling functionality."""
+    step1 = MockStep("step1")
+    step2 = MockStep("step2")
+    pipeline = RobotProcessor([step1, step2])
+
+    transition = create_transition()
+
+    profile_results = pipeline.profile_steps(transition, num_runs=10)
+
+    assert len(profile_results) == 2
+    assert "step_0_MockStep" in profile_results
+    assert "step_1_MockStep" in profile_results
+    assert all(isinstance(time, float) and time >= 0 for time in profile_results.values())
+
+
 def test_save_and_load_pretrained():
     """Test saving and loading pipeline.
 
@@ -521,7 +571,7 @@ def test_save_and_load_pretrained():
     step1.counter = 5
     step2.counter = 10
 
-    pipeline = RobotProcessor([step1, step2], name="TestPipeline")
+    pipeline = RobotProcessor([step1, step2], name="TestPipeline", seed=42)
 
     with tempfile.TemporaryDirectory() as tmp_dir:
         # Save pipeline
@@ -536,6 +586,7 @@ def test_save_and_load_pretrained():
             config = json.load(f)
 
         assert config["name"] == "TestPipeline"
+        assert config["seed"] == 42
         assert len(config["steps"]) == 2
 
         # Verify counters are saved in config, not in separate state files
@@ -546,6 +597,7 @@ def test_save_and_load_pretrained():
         loaded_pipeline = RobotProcessor.from_pretrained(tmp_dir)
 
         assert loaded_pipeline.name == "TestPipeline"
+        assert loaded_pipeline.seed == 42
         assert len(loaded_pipeline) == 2
 
         # Check that counter was restored from config
@@ -667,6 +719,182 @@ class MockModuleStep(nn.Module):
         return features
 
 
+def test_to_device_with_state_dict():
+    """Test moving pipeline to device for steps with state_dict."""
+    step = MockStepWithTensorState(name="device_test", window_size=5)
+    pipeline = RobotProcessor([step])
+
+    # Process some transitions to populate state
+    for i in range(10):
+        transition = create_transition(reward=float(i))
+        pipeline(transition)
+
+    # Check initial device (should be CPU)
+    assert step.running_mean.device.type == "cpu"
+    assert step.running_count.device.type == "cpu"
+
+    # Move to same device (CPU)
+    result = pipeline.to("cpu")
+    assert result is pipeline  # Check it returns self
+    assert step.running_mean.device.type == "cpu"
+    assert step.running_count.device.type == "cpu"
+
+    # Test with torch.device object
+    result = pipeline.to(torch.device("cpu"))
+    assert result is pipeline
+    assert step.running_mean.device.type == "cpu"
+
+    # If CUDA is available, test GPU transfer
+    if torch.cuda.is_available():
+        result = pipeline.to("cuda")
+        assert result is pipeline
+        assert step.running_mean.device.type == "cuda"
+        assert step.running_count.device.type == "cuda"
+
+        # Move back to CPU
+        pipeline.to("cpu")
+        assert step.running_mean.device.type == "cpu"
+        assert step.running_count.device.type == "cpu"
+
+
+def test_to_device_with_module():
+    """Test moving pipeline to device for steps that inherit from nn.Module.
+
+    Even though the step inherits from nn.Module, the pipeline will use the
+    state_dict/load_state_dict approach to move tensors to the device.
+    """
+    module_step = MockModuleStep(input_dim=5, hidden_dim=3)
+    pipeline = RobotProcessor([module_step])
+
+    # Process some data
+    obs = torch.randn(2, 5)
+    transition = create_transition(observation=obs, reward=1.0)
+    pipeline(transition)
+
+    # Check initial device
+    assert module_step.linear.weight.device.type == "cpu"
+    assert module_step.running_mean.device.type == "cpu"
+
+    # Move to same device
+    result = pipeline.to("cpu")
+    assert result is pipeline
+    assert module_step.linear.weight.device.type == "cpu"
+    assert module_step.running_mean.device.type == "cpu"
+
+    # If CUDA is available, test GPU transfer
+    if torch.cuda.is_available():
+        result = pipeline.to("cuda:0")
+        assert result is pipeline
+        assert module_step.linear.weight.device.type == "cuda"
+        assert module_step.linear.weight.device.index == 0
+        assert module_step.running_mean.device.type == "cuda"
+        assert module_step.running_mean.device.index == 0
+
+        # Verify the module still works after transfer
+        obs_cuda = torch.randn(2, 5, device="cuda:0")
+        transition = create_transition(observation=obs_cuda, reward=1.0)
+        pipeline(transition)  # Should not raise an error
+
+
+def test_to_device_mixed_steps():
+    """Test moving pipeline with various types of steps, all using state_dict approach."""
+    module_step = MockModuleStep()
+    state_dict_step = MockStepWithTensorState()
+    simple_step = MockStepWithoutOptionalMethods()  # No tensor state
+
+    pipeline = RobotProcessor([module_step, state_dict_step, simple_step])
+
+    # Process some data
+    for i in range(5):
+        transition = create_transition(observation=torch.randn(2, 10), reward=float(i))
+        pipeline(transition)
+
+    # Check initial state
+    assert module_step.linear.weight.device.type == "cpu"
+    assert state_dict_step.running_mean.device.type == "cpu"
+
+    # Move to device
+    result = pipeline.to("cpu")
+    assert result is pipeline
+
+    if torch.cuda.is_available():
+        pipeline.to("cuda")
+        assert module_step.linear.weight.device.type == "cuda"
+        assert module_step.running_mean.device.type == "cuda"
+        assert state_dict_step.running_mean.device.type == "cuda"
+        assert state_dict_step.running_count.device.type == "cuda"
+
+
+def test_to_device_empty_state():
+    """Test moving pipeline with steps that have empty state_dict."""
+    step = MockStep("empty_state")  # This step has empty state_dict
+    pipeline = RobotProcessor([step])
+
+    # Should not raise an error even with empty state
+    result = pipeline.to("cpu")
+    assert result is pipeline
+
+    if torch.cuda.is_available():
+        result = pipeline.to("cuda")
+        assert result is pipeline
+
+
+def test_to_device_preserves_functionality():
+    """Test that pipeline functionality is preserved after device transfer."""
+    step = MockStepWithTensorState(window_size=3)
+    pipeline = RobotProcessor([step])
+
+    # Process initial data
+    rewards = [1.0, 2.0, 3.0]
+    for r in rewards:
+        transition = create_transition(reward=r)
+        pipeline(transition)
+
+    # Check state before transfer
+    initial_mean = step.running_mean.clone()
+    initial_count = step.running_count.clone()
+
+    # Move to device (CPU to CPU in this case, but tests the mechanism)
+    pipeline.to("cpu")
+
+    # Verify state is preserved
+    assert torch.allclose(step.running_mean, initial_mean)
+    assert step.running_count == initial_count
+
+    # Process more data to ensure functionality
+    transition = create_transition(reward=4.0)
+    _ = pipeline(transition)
+
+    assert step.running_count == 4
+    assert step.running_mean[0] == 4.0  # First slot should have been overwritten with 4.0
+
+
+def test_to_device_invalid_device():
+    """Test error handling for invalid devices."""
+    pipeline = RobotProcessor([MockStep()])
+
+    # Invalid device names should raise an error from PyTorch
+    with pytest.raises(RuntimeError):
+        pipeline.to("invalid_device")
+
+
+def test_to_device_chaining():
+    """Test that to() returns self for method chaining."""
+    step1 = MockStepWithTensorState()
+    step2 = MockModuleStep()
+    pipeline = RobotProcessor([step1, step2])
+
+    # Test chaining
+    result = pipeline.to("cpu").reset()
+    assert result is None  # reset() returns None
+
+    # Can chain multiple to() calls
+    result1 = pipeline.to("cpu")
+    result2 = result1.to("cpu")
+    assert result1 is pipeline
+    assert result2 is pipeline
+
+
 class MockNonModuleStepWithState:
     """Mock step that explicitly does NOT inherit from nn.Module but has tensor state.
 
@@ -749,6 +977,129 @@ class MockNonModuleStepWithState:
         return features
 
 
+def test_to_device_non_module_class():
+    """Test moving pipeline to device for regular classes (non nn.Module) with tensor state.
+
+    This ensures the state_dict/load_state_dict approach works for classes that
+    don't inherit from nn.Module but still have tensor state to manage.
+    """
+    # Create a non-module step with tensor state
+    non_module_step = MockNonModuleStepWithState(name="device_test", feature_dim=5)
+    pipeline = RobotProcessor([non_module_step])
+
+    # Process some data to populate state
+    for i in range(3):
+        obs = torch.randn(2, 5)
+        transition = create_transition(observation=obs, reward=float(i))
+        result = pipeline(transition)
+        comp_data = result[TransitionKey.COMPLEMENTARY_DATA]
+        assert f"{non_module_step.name}_steps" in comp_data
+
+    # Verify all tensors are on CPU initially
+    assert non_module_step.weights.device.type == "cpu"
+    assert non_module_step.bias.device.type == "cpu"
+    assert non_module_step.running_stats.device.type == "cpu"
+    assert non_module_step.step_count.device.type == "cpu"
+
+    # Verify step count
+    assert non_module_step.step_count.item() == 3
+
+    # Store initial values for comparison
+    initial_weights = non_module_step.weights.clone()
+    initial_bias = non_module_step.bias.clone()
+    initial_stats = non_module_step.running_stats.clone()
+
+    # Move to same device (CPU)
+    result = pipeline.to("cpu")
+    assert result is pipeline
+
+    # Verify tensors are still on CPU and values unchanged
+    assert non_module_step.weights.device.type == "cpu"
+    assert torch.allclose(non_module_step.weights, initial_weights)
+    assert torch.allclose(non_module_step.bias, initial_bias)
+    assert torch.allclose(non_module_step.running_stats, initial_stats)
+
+    # If CUDA is available, test GPU transfer
+    if torch.cuda.is_available():
+        # Move to GPU
+        pipeline.to("cuda")
+
+        # Verify all tensors moved to GPU
+        assert non_module_step.weights.device.type == "cuda"
+        assert non_module_step.bias.device.type == "cuda"
+        assert non_module_step.running_stats.device.type == "cuda"
+        assert non_module_step.step_count.device.type == "cuda"
+
+        # Verify values are preserved
+        assert torch.allclose(non_module_step.weights.cpu(), initial_weights)
+        assert torch.allclose(non_module_step.bias.cpu(), initial_bias)
+        assert torch.allclose(non_module_step.running_stats.cpu(), initial_stats)
+        assert non_module_step.step_count.item() == 3
+
+        # Test that step still works on GPU
+        obs_gpu = torch.randn(2, 5, device="cuda")
+        transition = create_transition(observation=obs_gpu, reward=1.0)
+        result = pipeline(transition)
+        comp_data = result[TransitionKey.COMPLEMENTARY_DATA]
+
+        # Verify processing worked
+        assert comp_data[f"{non_module_step.name}_steps"] == 4
+
+        # Move back to CPU
+        pipeline.to("cpu")
+        assert non_module_step.weights.device.type == "cpu"
+        assert non_module_step.step_count.item() == 4
+
+
+def test_to_device_module_vs_non_module():
+    """Test that both nn.Module and non-Module steps work with the same state_dict approach."""
+    # Create both types of steps
+    module_step = MockModuleStep(input_dim=5, hidden_dim=3)
+    non_module_step = MockNonModuleStepWithState(name="non_module", feature_dim=5)
+
+    # Create pipeline with both
+    pipeline = RobotProcessor([module_step, non_module_step])
+
+    # Process some data
+    obs = torch.randn(2, 5)
+    transition = create_transition(observation=obs, reward=1.0)
+    _ = pipeline(transition)
+
+    # Check initial devices
+    assert module_step.linear.weight.device.type == "cpu"
+    assert module_step.running_mean.device.type == "cpu"
+    assert non_module_step.weights.device.type == "cpu"
+    assert non_module_step.running_stats.device.type == "cpu"
+
+    # Both should have been called
+    assert module_step.counter == 1
+    assert non_module_step.step_count.item() == 1
+
+    if torch.cuda.is_available():
+        # Move to GPU
+        pipeline.to("cuda")
+
+        # Verify both types of steps moved correctly
+        assert module_step.linear.weight.device.type == "cuda"
+        assert module_step.running_mean.device.type == "cuda"
+        assert non_module_step.weights.device.type == "cuda"
+        assert non_module_step.running_stats.device.type == "cuda"
+
+        # Process data on GPU
+        obs_gpu = torch.randn(2, 5, device="cuda")
+        transition = create_transition(observation=obs_gpu, reward=2.0)
+        _ = pipeline(transition)
+
+        # Verify both steps processed the data
+        assert module_step.counter == 2
+        assert non_module_step.step_count.item() == 2
+
+        # Move back to CPU and verify
+        pipeline.to("cpu")
+        assert module_step.linear.weight.device.type == "cpu"
+        assert non_module_step.weights.device.type == "cpu"
+
+
 # Tests for overrides functionality
 @dataclass
 class MockStepWithNonSerializableParam:
@@ -1127,6 +1478,96 @@ def test_from_pretrained_override_error_messages():
         assert "registered_mock_step" in error_msg
 
 
+class MockStepWithMixedState:
+    """Mock step demonstrating proper separation of tensor and non-tensor state.
+
+    Non-tensor state should go in get_config(), only tensors in state_dict().
+    """
+
+    def __init__(self, name: str = "mixed_state"):
+        self.name = name
+        self.tensor_data = torch.randn(5)
+        self.numpy_data = np.array([1, 2, 3, 4, 5])  # Goes in config
+        self.scalar_value = 42  # Goes in config
+        self.list_value = [1, 2, 3]  # Goes in config
+
+    def __call__(self, transition: EnvTransition) -> EnvTransition:
+        # Simple pass-through
+        return transition
+
+    def state_dict(self) -> dict[str, torch.Tensor]:
+        """Return ONLY tensor state as per the type contract."""
+        return {
+            "tensor_data": self.tensor_data,
+        }
+
+    def load_state_dict(self, state: dict[str, torch.Tensor]) -> None:
+        """Load tensor state only."""
+        self.tensor_data = state["tensor_data"]
+
+    def get_config(self) -> dict[str, Any]:
+        """Non-tensor state goes here."""
+        return {
+            "name": self.name,
+            "numpy_data": self.numpy_data.tolist(),  # Convert to list for JSON serialization
+            "scalar_value": self.scalar_value,
+            "list_value": self.list_value,
+        }
+
+    def feature_contract(self, features: dict[str, PolicyFeature]) -> dict[str, PolicyFeature]:
+        # We do not test feature_contract here
+        return features
+
+
+def test_to_device_with_mixed_state_types():
+    """Test that to() only moves tensor state, while non-tensor state remains in config."""
+    step = MockStepWithMixedState()
+    pipeline = RobotProcessor([step])
+
+    # Store initial values
+    initial_numpy = step.numpy_data.copy()
+    initial_scalar = step.scalar_value
+    initial_list = step.list_value.copy()
+
+    # Check initial state
+    assert step.tensor_data.device.type == "cpu"
+    assert isinstance(step.numpy_data, np.ndarray)
+    assert isinstance(step.scalar_value, int)
+    assert isinstance(step.list_value, list)
+
+    # Verify state_dict only contains tensors
+    state = step.state_dict()
+    assert all(isinstance(v, torch.Tensor) for v in state.values())
+    assert "tensor_data" in state
+    assert "numpy_data" not in state
+
+    # Move to same device
+    pipeline.to("cpu")
+
+    # Verify tensor moved and non-tensor attributes unchanged
+    assert step.tensor_data.device.type == "cpu"
+    assert np.array_equal(step.numpy_data, initial_numpy)
+    assert step.scalar_value == initial_scalar
+    assert step.list_value == initial_list
+
+    if torch.cuda.is_available():
+        # Move to GPU
+        pipeline.to("cuda")
+
+        # Only tensor should move to GPU
+        assert step.tensor_data.device.type == "cuda"
+
+        # Non-tensor values should remain unchanged
+        assert isinstance(step.numpy_data, np.ndarray)
+        assert np.array_equal(step.numpy_data, initial_numpy)
+        assert step.scalar_value == initial_scalar
+        assert step.list_value == initial_list
+
+        # Move back to CPU
+        pipeline.to("cpu")
+        assert step.tensor_data.device.type == "cpu"
+
+
 def test_repr_empty_processor():
     """Test __repr__ with empty processor."""
     pipeline = RobotProcessor()
@@ -1193,10 +1634,10 @@ def test_repr_with_custom_name():
 def test_repr_with_seed():
     """Test __repr__ with seed parameter."""
     step = MockStep("test_step")
-    pipeline = RobotProcessor([step])
+    pipeline = RobotProcessor([step], seed=42)
     repr_str = repr(pipeline)
 
-    expected = "RobotProcessor(name='RobotProcessor', steps=1: [MockStep])"
+    expected = "RobotProcessor(name='RobotProcessor', steps=1: [MockStep], seed=42)"
     assert repr_str == expected
 
 
@@ -1204,17 +1645,19 @@ def test_repr_with_custom_name_and_seed():
     """Test __repr__ with both custom name and seed."""
     step1 = MockStep("step1")
     step2 = MockStepWithoutOptionalMethods()
-    pipeline = RobotProcessor([step1, step2], name="MyProcessor")
+    pipeline = RobotProcessor([step1, step2], name="MyProcessor", seed=123)
     repr_str = repr(pipeline)
 
-    expected = "RobotProcessor(name='MyProcessor', steps=2: [MockStep, MockStepWithoutOptionalMethods])"
+    expected = (
+        "RobotProcessor(name='MyProcessor', steps=2: [MockStep, MockStepWithoutOptionalMethods], seed=123)"
+    )
     assert repr_str == expected
 
 
 def test_repr_without_seed():
     """Test __repr__ when seed is explicitly None (should not show seed)."""
     step = MockStep("test_step")
-    pipeline = RobotProcessor([step], name="TestProcessor")
+    pipeline = RobotProcessor([step], name="TestProcessor", seed=None)
     repr_str = repr(pipeline)
 
     expected = "RobotProcessor(name='TestProcessor', steps=1: [MockStep])"
@@ -1242,10 +1685,10 @@ def test_repr_edge_case_long_names():
     step3 = MockStepWithTensorState()
     step4 = MockNonModuleStepWithState()
 
-    pipeline = RobotProcessor([step1, step2, step3, step4], name="LongNames")
+    pipeline = RobotProcessor([step1, step2, step3, step4], name="LongNames", seed=999)
     repr_str = repr(pipeline)
 
-    expected = "RobotProcessor(name='LongNames', steps=4: [MockStepWithNonSerializableParam, MockStepWithoutOptionalMethods, ..., MockNonModuleStepWithState])"
+    expected = "RobotProcessor(name='LongNames', steps=4: [MockStepWithNonSerializableParam, MockStepWithoutOptionalMethods, ..., MockNonModuleStepWithState], seed=999)"
     assert repr_str == expected