fix(ci): downgrade contents permission to read in claude.yml

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.github/CLAUDE.md

@@ -0,0 +1,86 @@
+# LeRobot — Claude Code Instructions
+
+You are a senior robotics ML engineer reviewing code for **LeRobot**, a PyTorch framework for real-world robot learning.
+Apply these principles to every PR review, fix, or task.
+
+---
+
+## Core Abstractions
+
+These are the load-bearing types. Handle them with care — breaking changes here affect every user.
+
+| Type             | Location                     | Role                                                         |
+| ---------------- | ---------------------------- | ------------------------------------------------------------ |
+| `LeRobotDataset` | `src/lerobot/datasets/`      | Streaming replay buffer; HF Hub integration                  |
+| `Policy`         | `src/lerobot/policies/`      | Base class for all learning agents (ACT, Diffusion, SARM, …) |
+| `Robot`          | `src/lerobot/robots/`        | Hardware abstraction; carries `_output_pipeline`             |
+| `Teleoperator`   | `src/lerobot/teleoperators/` | Leader-side hardware abstraction; carries `_output_pipeline` |
+| `Env`            | `src/lerobot/envs/`          | Gym-like robotics environments                               |
+| `Processor`      | `src/lerobot/processor/`     | Data transformation pipelines attached to robots/teleops     |
+
+**Never break their public APIs without a migration note and explicit user approval.**
+
+---
+
+## Engineering Principles
+
+### Code quality
+
+- Explicit over magic — no hidden control flow, no implicit state.
+- No deep inheritance trees. Prefer composition.
+- No decorative comment separators (`===`, `---`, etc.).
+- Add comments only where the logic is non-obvious.
+- No over-engineering. YAGNI applies strictly.
+
+### Type safety
+
+- All new and modified Python code must be fully typed (PEP 484).
+- `mypy --strict` must pass on changed files.
+- Do not widen or weaken existing type signatures.
+
+### Backwards compatibility
+
+- Public API changes require migration notes.
+- Additive changes are preferred over modifications.
+- `so100_follower` / `so101_follower` are aliases — never bleed changes there unintentionally.
+
+### HF ecosystem
+
+- Use `push_to_hub()`, HF Hub dataset streaming, and `evaluate` scripts.
+- Dataset changes must preserve streaming compatibility.
+- Prefer reusing HF primitives over rolling custom solutions.
+
+---
+
+## PR Review Checklist
+
+Before approving or marking P1 issues resolved, verify:
+
+- [ ] `pre-commit run -a` would pass (ruff, mypy, typos, zizmor, bandit)
+- [ ] All new/modified code is typed and passes `mypy --strict`
+- [ ] New features have unit tests; no silent behavioral changes
+- [ ] Public APIs of `LeRobotDataset`, `Policy`, `Robot`, `Teleoperator`, `Env` are unchanged (or migration note present)
+- [ ] HF Hub streaming still works for dataset changes
+- [ ] No unnecessary abstractions introduced
+- [ ] No breaking changes to training scripts (`lerobot-train`, `lerobot-eval`, `lerobot-record`)
+
+---
+
+## ML-Specific Checks
+
+Flag these as **P1** if found:
+
+- **Data leakage**: train and val/test splits must be constructed before any normalization or augmentation that uses train statistics.
+- **Loss function errors**: verify reduction mode (`mean` vs `sum`), correct masking, correct shape alignment.
+- **Gradient flow**: new modules must have gradients flowing (check `requires_grad`, no detached tensors in the loss path by accident).
+- **Distributed training**: operations on tensors must be DDP-safe; no in-place ops on parameters; batch norm needs `SyncBatchNorm` if used.
+- **Memory leaks**: no accumulation of tensors outside the training loop; `optimizer.zero_grad()` called correctly.
+
+---
+
+## What to Skip
+
+- Don't flag style nitpicks on unchanged surrounding code.
+- Don't propose refactors outside the PR's scope.
+- Don't add docstrings or comments to code the PR didn't touch.
+- Don't suggest speculative future features (YAGNI).

.github/workflows/claude-code-review.yml

@@ -0,0 +1,49 @@
+name: Claude Code Review
+
+on:
+  pull_request:
+    types: [opened, synchronize, ready_for_review, reopened]
+
+jobs:
+  claude-review:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: read
+      id-token: write
+      actions: read
+    env:
+      FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Run Claude Code Review
+        id: claude-review
+        uses: anthropics/claude-code-action@26ddc358fe3befff50c5ec2f80304c90c763f6f8 # v1
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          use_sticky_comment: true
+          prompt: |
+            Read `.github/CLAUDE.md` for lerobot-specific conventions, then review this PR.
+            Provide structured, actionable feedback.
+
+            Focus areas (in priority order):
+            1. **Correctness**: Logic errors, off-by-ones, wrong tensor shapes, incorrect loss functions
+            2. **Type safety**: All new/modified Python code must pass `mypy --strict`; check for missing annotations
+            3. **Backwards compatibility**: Does this break `LeRobotDataset`, `Policy`, `Robot`, `Teleoperator`, `Env`, or `Processor` public APIs?
+            4. **Tests**: New features must have tests; no silent behavioral changes
+            5. **Code style**: Explicit over magic, no unnecessary abstractions, no decorative comments
+            6. **HF integration**: Dataset streaming, `push_to_hub`, HF Hub compatibility preserved?
+            7. **pre-commit**: Would `pre-commit run -a` pass? (ruff, mypy, typos, zizmor)
+
+            Format findings as P1 (must fix) / P2 (should fix) / P3 (nice to have).
+            Skip P3 if the PR is already high quality.
+          claude_args: '--model claude-opus-4-6'
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options

.github/workflows/claude.yml

@@ -0,0 +1,58 @@
+name: Claude Code
+
+on:
+  issue_comment:
+    types: [created]
+  pull_request_review_comment:
+    types: [created]
+  issues:
+    types: [opened, assigned]
+  pull_request_review:
+    types: [submitted]
+
+jobs:
+  claude:
+    if: |
+      (github.event_name == 'issue_comment' &&
+       contains(github.event.comment.body, '@claude') &&
+       (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR')) ||
+      (github.event_name == 'pull_request_review_comment' &&
+       contains(github.event.comment.body, '@claude') &&
+       (github.event.comment.author_association == 'OWNER' || github.event.comment.author_association == 'MEMBER' || github.event.comment.author_association == 'COLLABORATOR')) ||
+      (github.event_name == 'pull_request_review' &&
+       contains(github.event.review.body, '@claude') &&
+       (github.event.review.author_association == 'OWNER' || github.event.review.author_association == 'MEMBER' || github.event.review.author_association == 'COLLABORATOR')) ||
+      (github.event_name == 'issues' &&
+       (contains(github.event.issue.body, '@claude') || contains(github.event.issue.title, '@claude')) &&
+       (github.event.issue.author_association == 'OWNER' || github.event.issue.author_association == 'MEMBER' || github.event.issue.author_association == 'COLLABORATOR'))
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      pull-requests: write
+      issues: write
+      id-token: write
+      actions: read
+    env:
+      FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true
+
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 1
+          persist-credentials: false
+
+      - name: Run Claude Code
+        id: claude
+        uses: anthropics/claude-code-action@26ddc358fe3befff50c5ec2f80304c90c763f6f8 # v1
+        with:
+          anthropic_api_key: ${{ secrets.ANTHROPIC_API_KEY }}
+          use_sticky_comment: true
+
+          # This is an optional setting that allows Claude to read CI results on PRs
+          additional_permissions: |
+            actions: read
+
+          claude_args: '--system-prompt "Read .github/CLAUDE.md for lerobot-specific conventions before responding."'
+          # See https://github.com/anthropics/claude-code-action/blob/main/docs/usage.md
+          # or https://code.claude.com/docs/en/cli-reference for available options

.github/workflows/docker_publish.yml

@@ -12,8 +12,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# This workflow handles nightly testing & docker images publishing.
+# This workflow handles Docker image publishing & testing.
-name: Nightly
+name: Docker Publish & Test
 permissions:
   contents: read
 
@@ -39,8 +39,8 @@ concurrency:
 
 jobs:
   # This job builds a CPU image for testing & distribution
-  build-docker-cpu-nightly:
+  build-docker-cpu:
-    name: Build CPU Docker for Nightly
+    name: Build CPU Docker
     runs-on:
       group: aws-general-8-plus
     if: github.repository == 'huggingface/lerobot'
@@ -74,8 +74,8 @@ jobs:
           tags: ${{ env.DOCKER_IMAGE_NAME_CPU }}
 
   # This job builds a GPU image for testing & distribution
-  build-docker-gpu-nightly:
+  build-docker-gpu:
-    name: Build GPU Docker for Nightly
+    name: Build GPU Docker
     runs-on:
       group: aws-general-8-plus
     if: github.repository == 'huggingface/lerobot'
@@ -109,9 +109,9 @@ jobs:
           tags: ${{ env.DOCKER_IMAGE_NAME_GPU }}
 
   # This job runs the E2E tests + pytest with all extras in the CPU image
-  nightly-cpu-tests:
+  cpu-tests:
-    name: Nightly CPU Tests
+    name: CPU Tests
-    needs: [build-docker-cpu-nightly]
+    needs: [build-docker-cpu]
     runs-on:
       group: aws-g6-4xlarge-plus
     env:
@@ -121,7 +121,7 @@ jobs:
       TRITON_CACHE_DIR: /home/user_lerobot/.cache/triton
       HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
     container:
-      image: ${{ needs.build-docker-cpu-nightly.outputs.image_tag }} # zizmor: ignore[unpinned-images]
+      image: ${{ needs.build-docker-cpu.outputs.image_tag }} # zizmor: ignore[unpinned-images]
       options: --shm-size "16gb"
       credentials:
         username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
@@ -142,9 +142,9 @@ jobs:
         run: make test-end-to-end
 
   # This job runs the E2E tests + pytest with all extras in the GPU image
-  nightly-gpu-tests:
+  gpu-tests:
-    name: Nightly GPU Tests
+    name: GPU Tests
-    needs: [build-docker-gpu-nightly]
+    needs: [build-docker-gpu]
     runs-on:
       group: aws-g6-4xlarge-plus
     env:
@@ -154,7 +154,7 @@ jobs:
       TRITON_CACHE_DIR: /home/user_lerobot/.cache/triton
       HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
     container:
-      image: ${{ needs.build-docker-gpu-nightly.outputs.image_tag }} # zizmor: ignore[unpinned-images]
+      image: ${{ needs.build-docker-gpu.outputs.image_tag }} # zizmor: ignore[unpinned-images]
       options: --gpus all --shm-size "16gb"
       credentials:
         username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
@@ -175,9 +175,9 @@ jobs:
         run: make test-end-to-end
 
   # This job runs multi-GPU training tests with 4 GPUs
-  nightly-multi-gpu-tests:
+  multi-gpu-tests:
-    name: Nightly Multi-GPU Tests
+    name: Multi-GPU Tests
-    needs: [build-docker-gpu-nightly]
+    needs: [build-docker-gpu]
     runs-on:
       group: aws-g4dn-12xlarge  # Instance with 4 GPUs
     env:
@@ -188,7 +188,7 @@ jobs:
       CUDA_VISIBLE_DEVICES: "0,1,2,3"
       HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
     container:
-      image: ${{ needs.build-docker-gpu-nightly.outputs.image_tag }} # zizmor: ignore[unpinned-images]
+      image: ${{ needs.build-docker-gpu.outputs.image_tag }} # zizmor: ignore[unpinned-images]
       options: --gpus all --shm-size "16gb"
       credentials:
         username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}

.github/workflows/documentation-upload-pr.yml

@@ -33,7 +33,7 @@ jobs:
       github.event.workflow_run.event == 'pull_request' &&
       github.event.workflow_run.conclusion == 'success' &&
       github.repository == 'huggingface/lerobot'
-    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@main
+    uses: huggingface/doc-builder/.github/workflows/upload_pr_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
     with:
       package_name: lerobot
     secrets:

.github/workflows/documentation.yml

@@ -55,7 +55,7 @@ jobs:
       github.repository == 'huggingface/lerobot'
     permissions:
       contents: read
-    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
     with:
       commit_sha: ${{ github.sha }}
       package: lerobot
@@ -78,7 +78,7 @@ jobs:
     permissions:
       contents: read
       pull-requests: write
-    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
+    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@90b4ee2c10b81b5c1a6367c4e6fc9e2fb510a7e3  # main
     with:
       commit_sha: ${{ github.event.pull_request.head.sha }}
       pr_number: ${{ github.event.number }}

.github/workflows/fast_tests.yml

@@ -27,6 +27,7 @@ on:
       - "tests/**"
       - ".github/workflows/**"
       - "pyproject.toml"
+      - "uv.lock"
       - "Makefile"
   push:
     branches:
@@ -36,6 +37,7 @@ on:
       - "tests/**"
       - ".github/workflows/**"
       - "pyproject.toml"
+      - "uv.lock"
       - "Makefile"
 
 permissions:
@@ -63,7 +65,7 @@ jobs:
       HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
       HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           persist-credentials: false
           lfs: true
@@ -81,14 +83,14 @@ jobs:
           libusb-1.0-0-dev speech-dispatcher libgeos-dev portaudio19-dev
 
       - name: Setup uv and Python
-        uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
+        uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e  # v6
         with:
           enable-cache: true
           version: ${{ env.UV_VERSION }}
           python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Install lerobot with test extras
-        run: uv sync --extra "test"
+        run: uv sync --locked --extra "test"
 
       - name: Login to Hugging Face
         if: env.HF_USER_TOKEN != ''

.github/workflows/full_tests.yml

@@ -29,6 +29,7 @@ on:
       - "tests/**"
       - ".github/workflows/**"
       - "pyproject.toml"
+      - "uv.lock"
       - "Makefile"
 
 permissions:
@@ -62,7 +63,7 @@ jobs:
       HF_LEROBOT_HOME: /mnt/cache/.cache/huggingface/lerobot
       HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           lfs: true
           persist-credentials: false
@@ -79,14 +80,14 @@ jobs:
           speech-dispatcher libgeos-dev portaudio19-dev
 
       - name: Setup uv and Python
-        uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
+        uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e  # v6
         with:
           enable-cache: true
           version: ${{ env.UV_VERSION }}
           python-version: ${{ env.PYTHON_VERSION }}
 
       - name: Install lerobot with all extras
-        run: uv sync --extra all # TODO(Steven): Make flash-attn optional
+        run: uv sync --locked --extra all # TODO(Steven): Make flash-attn optional
 
       - name: Login to Hugging Face
         if: env.HF_USER_TOKEN != ''
@@ -136,21 +137,21 @@ jobs:
           sudo apt-get update
           sudo apt-get install git-lfs
           git lfs install
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           lfs: true
           persist-credentials: false
       - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
+        uses: docker/setup-buildx-action@8d2750c68a42422c14e847fe6c8ac0403b4cbd6f  # v3
         with:
           cache-binary: false
       - name: Login to Docker Hub
-        uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
+        uses: docker/login-action@c94ce9fb468520275223c153574b00df6fe4bcc9  # v3
         with:
           username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
           password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
       - name: Build and push Docker image
-        uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
+        uses: docker/build-push-action@10e90e3645eae34f1e60eeb005ba3a3d33f178e8  # v6
         with:
           context: .
           file: ./docker/Dockerfile.internal

.github/workflows/latest_deps_tests.yml

@@ -12,38 +12,81 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-# This workflow handles full testing with unboud dependencies versions.
+# This workflow tests the project against the latest upstream dependencies
-name: Unbound Dependency Tests
+# (within pyproject.toml constraints) and opens a PR to update uv.lock
+# if the tests pass and the lockfile has changed.
+name: Latest Dependency Tests
 
 on:
   # Allows running this workflow manually from the Actions tab
   workflow_dispatch:
 
-  # Run on the 1st and 15th of every month at 09:00 UTC
+  # Runs at 03:00 UTC
-  # schedule:
+  schedule:
-  #  - cron: '0 2 1,15 * *'
+    - cron: "0 3 * * *"
-
-permissions:
-  contents: read
 
 # Sets up the environment variables
 env:
   UV_VERSION: "0.8.0"
   PYTHON_VERSION: "3.12"
-  DOCKER_IMAGE_NAME: huggingface/lerobot-gpu:unbound
+  DOCKER_IMAGE_NAME: huggingface/lerobot-gpu:latest-deps
 
-# Ensures that only the latest action is built, canceling older runs.
+# Ensures that only the latest run is active, canceling older runs.
 concurrency:
-  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  group: ${{ github.workflow }}
   cancel-in-progress: true
 
 jobs:
 
-  # This job runs the E2E tests + pytest with all unbound extras
+  # This job upgrades the lockfile and checks if dependencies have changed
-  full-tests:
+  upgrade-lock:
-    name: Full Unbound Tests
+    name: Upgrade Lockfile
     runs-on: ubuntu-latest
     if: github.repository == 'huggingface/lerobot'
+    permissions:
+      contents: read
+    outputs:
+      changed: ${{ steps.diff.outputs.changed }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Setup uv and Python
+        uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
+        with:
+          version: ${{ env.UV_VERSION }}
+          python-version: ${{ env.PYTHON_VERSION }}
+
+      - name: Upgrade uv.lock
+        run: uv lock --upgrade
+
+      - name: Check for changes
+        id: diff
+        run: |
+          if git diff --quiet uv.lock; then
+            echo "changed=false" >> "$GITHUB_OUTPUT"
+            echo "uv.lock is up to date — no dependency changes."
+          else
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+            echo "uv.lock has changed — running tests."
+          fi
+
+      - name: Upload updated lockfile
+        if: steps.diff.outputs.changed == 'true'
+        uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
+        with:
+          name: uv-lock
+          path: uv.lock
+
+  # This job runs the full test suite with the upgraded dependencies
+  cpu-tests:
+    name: CPU Tests (Latest Deps)
+    needs: [upgrade-lock]
+    if: needs.upgrade-lock.outputs.changed == 'true'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
     env:
       MUJOCO_GL: egl
       HF_HOME: /mnt/cache/.cache/huggingface
@@ -55,6 +98,11 @@ jobs:
           lfs: true
           persist-credentials: false
 
+      - name: Download updated lockfile
+        uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
+        with:
+          name: uv-lock
+
       # NOTE(Steven): Mount to `/mnt` to avoid the limited storage on `/home`. Consider cleaning default SDKs or using self-hosted runners for more space.
       # (As of 2024-06-10, the runner's `/home` has only 6.2 GB free—8% of its 72 GB total.)
       - name: Setup /mnt storage
@@ -73,34 +121,32 @@ jobs:
           version: ${{ env.UV_VERSION }}
           python-version: ${{ env.PYTHON_VERSION }}
 
-      - name: Unbound dependencies
-        run: |
-          sed -i 's/,[[:space:]]*<[0-9\.]*//g' pyproject.toml
-          echo "Dependencies unbound:" && cat pyproject.toml
-
       - name: Install lerobot with all extras
-        run: uv sync --extra all # TODO(Steven): Make flash-attn optional
+        run: uv sync --locked --extra all # TODO(Steven): Make flash-attn optional
+
       - name: Login to Hugging Face
         if: env.HF_USER_TOKEN != ''
         run: |
           uv run hf auth login --token "$HF_USER_TOKEN" --add-to-git-credential
           uv run hf auth whoami
+
       - name: Run pytest (all extras)
-        run: uv run pytest tests -vv
+        run: uv run pytest tests -vv --maxfail=10
 
       - name: Run end-to-end tests
         run: uv run make test-end-to-end
 
-  # This job builds a GPU enabled image for testing
+  # This job builds a GPU-enabled Docker image with the upgraded dependencies
   build-and-push-docker:
     name: Build and Push Docker
+    needs: [upgrade-lock]
+    if: needs.upgrade-lock.outputs.changed == 'true'
+    permissions:
+      contents: read
     runs-on:
       group: aws-general-8-plus
-    if: github.repository == 'huggingface/lerobot'
     outputs:
       image_tag: ${{ env.DOCKER_IMAGE_NAME }}
-    env:
-      GITHUB_REF: ${{ github.ref }}
     steps:
       - name: Install Git LFS
         run: |
@@ -111,6 +157,12 @@ jobs:
         with:
           lfs: true
           persist-credentials: false
+
+      - name: Download updated lockfile
+        uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
+        with:
+          name: uv-lock
+
       - name: Set up Docker Buildx
         uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
         with:
@@ -127,14 +179,13 @@ jobs:
           file: ./docker/Dockerfile.internal
           push: true
           tags: ${{ env.DOCKER_IMAGE_NAME }}
-          build-args: |
-            UNBOUND_DEPS=true
 
-  # This job runs pytest with all unbound extras in a GPU enabled host
+  # This job runs pytest with all extras on a GPU-enabled host
-  # It runs everytime a test image is created
   gpu-tests:
-    name: GPU Unbound Tests
+    name: GPU Tests (Latest Deps)
     needs: [build-and-push-docker]
+    permissions:
+      contents: read
     runs-on:
       group: aws-g6-4xlarge-plus
     env:
@@ -159,17 +210,69 @@ jobs:
         run: |
           hf auth login --token "$HF_USER_TOKEN" --add-to-git-credential
           hf auth whoami
+      - name: Fix ptxas permissions
+        run: chmod +x /lerobot/.venv/lib/python3.12/site-packages/triton/backends/nvidia/bin/ptxas
       - name: Run pytest on GPU
-        run: pytest tests -vv
+        run: pytest tests -vv --maxfail=10
       - name: Run end-to-end tests
         run: make test-end-to-end
 
-  # This job deletes the test image recently created
+  # This job creates or updates a PR with the upgraded lockfile
-  # It runs everytime after the gpu-tests have finished
+  open-pr:
-  delete-unbound-image:
+    name: Open PR
-    name: Delete Unbound Image
+    needs: [cpu-tests, gpu-tests, upgrade-lock]
+    if: success() && needs.upgrade-lock.outputs.changed == 'true'
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      pull-requests: write
+    env:
+      GH_TOKEN: ${{ secrets.UPDATE_LOCK_TOKEN }}
+    steps:
+      - uses: actions/checkout@v6
+        with:
+          persist-credentials: false
+
+      - name: Download updated lockfile
+        uses: actions/download-artifact@v4 # zizmor: ignore[unpinned-uses]
+        with:
+          name: uv-lock
+
+      - name: Create or update PR
+        run: |
+          set -euo pipefail
+          BRANCH="auto/update-uv-lock"
+
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git remote set-url origin "https://x-access-token:${GH_TOKEN}@github.com/${{ github.repository }}.git"
+
+          git checkout -B "$BRANCH"
+          git add uv.lock
+          git commit -m "chore(dependencies): update uv.lock"
+          git push --force origin "$BRANCH"
+
+          # Create PR only if one doesn't already exist for this branch
+          EXISTING_PR=$(gh pr list --head "$BRANCH" --state open --json number --jq '.[0].number')
+          if [ -z "$EXISTING_PR" ]; then
+            gh pr create \
+              --title "chore(dependencies): update uv.lock" \
+              --body "Automated update of \`uv.lock\` after successful latest dependency tests (CPU + GPU).
+
+          This PR upgrades all dependencies to their latest versions within the ranges specified in \`pyproject.toml\`." \
+              --head "$BRANCH" \
+              --base main
+          else
+            echo "PR #$EXISTING_PR already exists, branch has been updated."
+          fi
+
+  # This job deletes the temporary Docker image after tests complete
+  cleanup-docker:
+    name: Cleanup Docker Image
     needs: [gpu-tests, build-and-push-docker]
     if: always() && needs.build-and-push-docker.result == 'success'
+    permissions:
+      contents: read
     runs-on: ubuntu-latest
     steps:
       - name: Get Docker Hub Token and Delete Image
@@ -180,8 +283,7 @@ jobs:
           IMAGE_FULL: ${{ needs.build-and-push-docker.outputs.image_tag }}
         run: |
           IMAGE_NAME=$(echo "$IMAGE_FULL" | cut -d':' -f1)
-          IMAGE_TAG=$(echo "$IMAGE_FULL" | cut -d':' -f2)
+          IMAGE_TAG=$(echo "$IMAGE_FULL" | cut -d':' -f2-)
-
           echo "Attempting to delete image: $IMAGE_NAME:$IMAGE_TAG"
 
           TOKEN=$(curl -s -H "Content-Type: application/json" \

.github/workflows/quality.yml

@@ -43,16 +43,16 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           persist-credentials: false
 
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: '3.12'
 
       - name: Run pre-commit hooks
-        uses: pre-commit/action@v3.0.1 # zizmor: ignore[unpinned-uses]
+        uses: pre-commit/action@2c7b3805fd2a0fd8c1884dcaebf91fc102a13ecd  # v3.0.1
         with:
           extra_args: --all-files --show-diff-on-failure --color=always

.github/workflows/release.yml

@@ -38,12 +38,12 @@ jobs:
 
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           persist-credentials: false
 
       - name: Set up Python
-        uses: actions/setup-python@v6
+        uses: actions/setup-python@a309ff8b426b58ec0e2a45f0f869d46889d02405  # v6
         with:
           python-version: '3.12'
 
@@ -104,7 +104,7 @@ jobs:
       - 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@v1.13.0 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e  # v1.13.0
         with:
           repository-url: https://test.pypi.org/legacy/
           verbose: true
@@ -112,7 +112,7 @@ jobs:
 
       - name: Publish to PyPI
         if: startsWith(github.ref, 'refs/tags/v') && !contains(github.ref, '-')
-        uses: pypa/gh-action-pypi-publish@v1.13.0 # zizmor: ignore[unpinned-uses, use-trusted-publishing]
+        uses: pypa/gh-action-pypi-publish@ed0c53931b1dc9bd32cbe73a98c7f6766f8a527e  # v1.13.0
         with:
           verbose: true
           print-hash: true
@@ -127,7 +127,7 @@ jobs:
     env:
       MUJOCO_GL: egl
     steps:
-      - uses: actions/checkout@v6
+      - uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           lfs: true
           persist-credentials: false
@@ -137,7 +137,7 @@ jobs:
           git curl libglib2.0-0 libegl1-mesa-dev ffmpeg libusb-1.0-0-dev \
           speech-dispatcher libgeos-dev portaudio19-dev
       - name: Setup uv and Python
-        uses: astral-sh/setup-uv@v6 # zizmor: ignore[unpinned-uses]
+        uses: astral-sh/setup-uv@d0cc045d04ccac9d8b7881df0226f9e82c39688e  # v6
         with:
           enable-cache: true # zizmor: ignore[cache-poisoning]
           version: ${{ env.UV_VERSION }}

.github/workflows/security.yml

@@ -43,12 +43,12 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout code
-        uses: actions/checkout@v6 # zizmor: ignore[unpinned-uses]
+        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd  # v6.0.2
         with:
           fetch-depth: 0
           persist-credentials: false
 
       - name: Secret Scanning
-        uses: trufflesecurity/trufflehog@v3.90.0  # zizmor: ignore[unpinned-uses]
+        uses: trufflesecurity/trufflehog@eafb8c5f6a06175141c27f17bcc17941853d0047  # v3.90.0
         with:
           extra_args: --only-verified

.gitignore

@@ -25,7 +25,6 @@ node_modules/
 
 # Lock files
 poetry.lock
-uv.lock
 Pipfile.lock
 
 ### Build & Distribution ###

README.md

@@ -4,7 +4,8 @@
 
 <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/latest_deps_tests.yml/badge.svg?branch=main)](https://github.com/huggingface/lerobot/actions/workflows/latest_deps_tests.yml?query=branch%3Amain)
+[![Tests](https://github.com/huggingface/lerobot/actions/workflows/docker_publish.yml/badge.svg?branch=main)](https://github.com/huggingface/lerobot/actions/workflows/docker_publish.yml?query=branch%3Amain)
 [![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/)

docker/Dockerfile.internal

@@ -73,17 +73,10 @@ ENV HOME=/home/user_lerobot \
 RUN uv venv --python python${PYTHON_VERSION}
 
 # Install Python dependencies for caching
-COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml README.md MANIFEST.in ./
+COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml uv.lock README.md MANIFEST.in ./
 COPY --chown=user_lerobot:user_lerobot src/ src/
 
-ARG UNBOUND_DEPS=false
+RUN uv sync --locked --extra all --no-cache
-
-RUN if [ "$UNBOUND_DEPS" = "true" ]; then \
-    sed -i 's/,[[:space:]]*<[0-9\.]*//g' pyproject.toml; \
-    echo "Dependencies unbound:" && cat pyproject.toml; \
-    fi
-
-RUN uv pip install --no-cache ".[all]"
 
 RUN chmod +x /lerobot/.venv/lib/python${PYTHON_VERSION}/site-packages/triton/backends/nvidia/bin/ptxas
 

docker/Dockerfile.user

@@ -61,17 +61,10 @@ ENV HOME=/home/user_lerobot \
 RUN uv venv
 
 # Install Python dependencies for caching
-COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml README.md MANIFEST.in ./
+COPY --chown=user_lerobot:user_lerobot setup.py pyproject.toml uv.lock README.md MANIFEST.in ./
 COPY --chown=user_lerobot:user_lerobot src/ src/
 
-ARG UNBOUND_DEPS=false
+RUN uv sync --locked --extra all --no-cache
-
-RUN if [ "$UNBOUND_DEPS" = "true" ]; then \
-    sed -i 's/,[[:space:]]*<[0-9\.]*//g' pyproject.toml; \
-    echo "Dependencies unbound:" && cat pyproject.toml; \
-    fi
-
-RUN uv pip install --no-cache ".[all]"
 
 # Copy the rest of the application code
 # Make sure to have the git-LFS files for testing

docker/README.md

@@ -0,0 +1,77 @@
+# Docker
+
+This directory contains Dockerfiles for running LeRobot in containerized environments. Both images are **built nightly from `main`** and published to Docker Hub with the full environment pre-baked — no dependency setup required.
+
+## Pre-built Images
+
+```bash
+# CPU-only image (based on Dockerfile.user)
+docker pull huggingface/lerobot-cpu:latest
+
+# GPU image with CUDA support (based on Dockerfile.internal)
+docker pull huggingface/lerobot-gpu:latest
+```
+
+## Quick Start
+
+The fastest way to start training is to pull the GPU image and run `lerobot-train` directly. This is the same environment used for all of our CI, so it is a well-tested, batteries-included setup.
+
+```bash
+docker run -it --rm --gpus all --shm-size 16gb huggingface/lerobot-gpu:latest
+
+# inside the container:
+lerobot-train --policy.type=act --dataset.repo_id=lerobot/aloha_sim_transfer_cube_human
+```
+
+## Dockerfiles
+
+### `Dockerfile.user` (CPU)
+
+A lightweight image based on `python:3.12-slim`. Includes all Python dependencies and system libraries but does not include CUDA — there is no GPU support. Useful for exploring the codebase, running scripts, or working with robots, but not practical for training.
+
+### `Dockerfile.internal` (GPU)
+
+A CUDA-enabled image based on `nvidia/cuda`. This is the image for training — mostly used for internal interactions with the GPU cluster.
+
+## Usage
+
+### Running a pre-built image
+
+```bash
+# CPU
+docker run -it --rm huggingface/lerobot-cpu:latest
+
+# GPU
+docker run -it --rm --gpus all --shm-size 16gb huggingface/lerobot-gpu:latest
+```
+
+### Building locally
+
+From the repo root:
+
+```bash
+# CPU
+docker build -f docker/Dockerfile.user -t lerobot-user .
+docker run -it --rm lerobot-user
+
+# GPU
+docker build -f docker/Dockerfile.internal -t lerobot-internal .
+docker run -it --rm --gpus all --shm-size 16gb lerobot-internal
+```
+
+### Multi-GPU training
+
+To select specific GPUs, set `CUDA_VISIBLE_DEVICES` when launching the container:
+
+```bash
+# Use 4 GPUs
+docker run -it --rm --gpus all --shm-size 16gb \
+  -e CUDA_VISIBLE_DEVICES=0,1,2,3 \
+  huggingface/lerobot-gpu:latest
+```
+
+### USB device access (e.g. robots, cameras)
+
+```bash
+docker run -it --device=/dev/ -v /dev/:/dev/ --rm huggingface/lerobot-cpu:latest
+```

docs/source/env_processor.mdx

@@ -90,11 +90,17 @@ The same policy can work with different environment processors, and the same env
 
 ```python
 # Use SmolVLA policy with LIBERO environment
-libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(libero_cfg)
+# Use SmolVLA policy with LIBERO environment
+libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
+    env_cfg=libero_cfg,
+    policy_cfg=smolvla_cfg,
+)
 smolvla_preprocessor, smolvla_postprocessor = make_pre_post_processors(smolvla_cfg)
-
 # Or use ACT policy with the same LIBERO environment
-libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(libero_cfg)
+libero_preprocessor, libero_postprocessor = make_env_pre_post_processors(
+    env_cfg=libero_cfg,
+    policy_cfg=act_cfg,
+)
 act_preprocessor, act_postprocessor = make_pre_post_processors(act_cfg)
 ```
 
@@ -203,7 +209,10 @@ def eval_main(cfg: EvalPipelineConfig):
     )
 
     # Create environment processors (NEW!)
-    env_preprocessor, env_postprocessor = make_env_pre_post_processors(env_cfg=cfg.env)
+    env_preprocessor, env_postprocessor = make_env_pre_post_processors(
+        env_cfg=cfg.env,
+        policy_cfg=cfg.policy,
+    )
 
     # Run evaluation with both processor types
     eval_policy_all(
@@ -307,21 +316,22 @@ class MyEnvProcessorStep(ObservationProcessorStep):
         return processed
 ```
 
-### 2. Update the Factory
+### 2. Update Your `EnvConfig` Subclass
 
 ```python
-# In src/lerobot/envs/factory.py
+# In src/lerobot/envs/configs.py
+@EnvConfig.register_subclass("myenv")
+@dataclass
+class MyEnvConfig(EnvConfig):
+    # ... task/features/gym kwargs ...
 
-def make_env_pre_post_processors(env_cfg: EnvConfig):
+    def get_env_processors(self):
-    if isinstance(env_cfg, LiberoEnv) or "libero" in env_cfg.type:
+        from lerobot.processor.pipeline import PolicyProcessorPipeline
-        preprocessor = PolicyProcessorPipeline(steps=[LiberoProcessorStep()])
-    elif isinstance(env_cfg, MyEnvConfig) or "myenv" in env_cfg.type:
-        preprocessor = PolicyProcessorPipeline(steps=[MyEnvProcessorStep()])
-    else:
-        preprocessor = PolicyProcessorPipeline(steps=[])
 
-    postprocessor = PolicyProcessorPipeline(steps=[])
+        return (
-    return preprocessor, postprocessor
+            PolicyProcessorPipeline(steps=[MyEnvProcessorStep()]),
+            PolicyProcessorPipeline(steps=[]),
+        )
 ```
 
 ### 3. Use in Evaluation

docs/source/groot.mdx

@@ -131,4 +131,4 @@ lerobot-record \
 
 ## License
 
-This model follows the **Apache 2.0 License**, consistent with the original [GR00T repository](https://github.com/NVIDIA/Isaac-GR00T).
+This model follows NVIDIA's proprietary license, consistent with the original [GR00T repository](https://github.com/NVIDIA/Isaac-GR00T). Future versions (starting from N1.7) will follow **Apache 2.0 License**.

docs/source/installation.mdx

@@ -1,6 +1,6 @@
 # Installation
 
-This guide uses `conda` (via miniforge) to manage environments (recommended). If you prefer another environment manager (e.g. `uv`, `venv`), ensure you have Python >=3.12 and `ffmpeg` installed with the `libsvtav1` encoder, then skip ahead to [Environment Setup](#step-2-environment-setup).
+This guide uses `conda` (via miniforge) to manage environments (recommended). If you prefer another environment manager (e.g. `uv`, `venv`), ensure you have Python >=3.12 and support PyTorch >= 2.10, then skip ahead to [Environment Setup](#step-2-environment-setup).
 
 ## Step 1 (`conda` only): Install [`miniforge`](https://conda-forge.org/download/)
 
@@ -20,7 +20,7 @@ Create a virtual environment with Python 3.12:
 conda create -y -n lerobot python=3.12
 ```
 </hfoption>
-<hfoption id="uv">
+<hfoption id="uv (PyTorch >= 2.10 only)">
 ```bash
 uv python install 3.12
 uv venv --python 3.12
@@ -32,48 +32,87 @@ uv venv --python 3.12
 Then activate your virtual environment, you have to do this each time you open a shell to use lerobot:
 
 <!-- prettier-ignore-start -->
+
 <hfoptions id="activate_venv">
-<hfoption id="conda">```bash
+<hfoption id="conda">
+```bash
 conda activate lerobot
-```</hfoption>
-<hfoption id="uv">
-```bash
-# Linux/macOSsource
-source .venv/bin/activate
-# Windows PowerShell
-source .venv\Scripts\Activate.ps1
 ```
-</hfoption>
-</hfoptions>
-<!-- prettier-ignore-end -->
-
-When using `conda`, install `ffmpeg` in your environment:
-
-```bash
-conda install ffmpeg -c conda-forge
-ffmpeg -version  # ffmpeg 8.X is not yet supported !
-```
-
-> [!TIP]
-> This usually installs `ffmpeg 7.X` for your platform compiled with the `libsvtav1` encoder. If `libsvtav1` is not supported (check supported encoders with `ffmpeg -encoders`), you can:
->
-> - _[On any platform]_ Explicitly install `ffmpeg 7.X` using:
->
-> ```bash
-> conda install ffmpeg=7.1.1 -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`.
 
 > [!NOTE]
-> When installing LeRobot inside WSL (Windows Subsystem for Linux), make sure to install `evdev` with the following command:
+> When installing LeRobot inside WSL (Windows Subsystem for Linux), make sure to also install `evdev`:
 >
 > ```bash
 > conda install evdev -c conda-forge
 > ```
 
+</hfoption>
+<hfoption id="uv (PyTorch >= 2.10 only)">
+```bash
+# Linux/macOS
+source .venv/bin/activate
+# Windows PowerShell
+.venv\Scripts\activate
+```
+
+> [!NOTE]
+> When installing LeRobot inside WSL (Windows Subsystem for Linux), make sure to also install `evdev`:
+>
+> ```bash
+> sudo apt install libevdev-dev
+> uv pip install evdev
+> ```
+
+</hfoption>
+</hfoptions>
+<!-- prettier-ignore-end -->
+
+### Install `ffmpeg` (for video decoding)
+
+LeRobot uses [TorchCodec](https://github.com/meta-pytorch/torchcodec) for video decoding by default, which requires `ffmpeg`.
+
+> [!NOTE]
+> **Platform support:** TorchCodec is **not available** on macOS Intel (x86_64), Linux ARM (aarch64, arm64, armv7l), or Windows with PyTorch < 2.8. On these platforms, LeRobot automatically falls back to `pyav` — so you do not need to install `ffmpeg` and can skip to Step 3.
+
+If your platform supports TorchCodec, install `ffmpeg` using one of the methods below:
+
+<!-- prettier-ignore-start -->
+
+<hfoptions id="install_ffmpeg">
+<hfoption id="conda (any PyTorch version)">
+
+Install `ffmpeg` in your conda environment. This works with **all PyTorch versions** and is **required for PyTorch < 2.10**:
+
+```bash
+conda install ffmpeg -c conda-forge
+```
+
+> [!TIP]
+> This usually installs `ffmpeg 8.X` with the `libsvtav1` encoder. If you run into issues (e.g. `libsvtav1` missing — check with `ffmpeg -encoders` — or a version mismatch with `torchcodec`), you can explicitly install `ffmpeg 7.1.1` using:
+>
+> ```bash
+> conda install ffmpeg=7.1.1 -c conda-forge
+> ```
+
+</hfoption>
+<hfoption id="uv (PyTorch >= 2.10 only)">
+
+Starting with **PyTorch >= 2.10** (TorchCodec ≥ 0.10), TorchCodec can dynamically link to a system-wide `ffmpeg` installation. This is useful when using `uv` or other non-`conda` environment managers:
+
+```bash
+# Ubuntu/Debian
+sudo apt install ffmpeg
+
+# macOS (Apple Silicon)
+brew install ffmpeg
+```
+
 > [!IMPORTANT]
-> If you are using `uv` you will have to install `ffmpeg` system-wide (outside of the virtual environment). You rely on `uv` and `torchcodec` ability to dynamically link to the system `ffmpeg`.
+> System-wide `ffmpeg` is **only supported with PyTorch >= 2.10** (TorchCodec ≥ 0.10). For older PyTorch versions, you **must** use `conda install ffmpeg -c conda-forge` instead.
+
+</hfoption>
+</hfoptions>
+<!-- prettier-ignore-end -->
 
 ## Step 3: Install LeRobot 🤗
 

docs/source/multi_task_dit.mdx

@@ -331,6 +331,54 @@ lerobot-train \
   --wandb.project=multitask_dit
 ```
 
+## Libero Results
+
+```
+python -m lerobot.scripts.lerobot_train \
+  --dataset.repo_id=HuggingFaceVLA/libero \
+  --policy.type=multi_task_dit \
+  --policy.push_to_hub=false \
+  --output_dir="./outputs/multitask_dit_libero" \
+  --job_name="multitask-dit-libero" \
+  --wandb.enable=true \
+  --wandb.project=multitask_dit_libero \
+  --dataset.image_transforms.enable=true \
+  --dataset.image_transforms.max_num_transforms=4 \
+  --dataset.image_transforms.tfs='{"brightness":{"type":"ColorJitter","kwargs":{"brightness":[0.75,1.25]}},"contrast":{"type":"ColorJitter","kwargs":{"contrast":[0.6,1.4]}},"saturation":{"type":"ColorJitter","kwargs":{"saturation":[0.8,1.2]}},"hue":{"type":"ColorJitter","kwargs":{"hue":[-0.05,0.05]}},"sharpness":{"type":"SharpnessJitter","kwargs":{"sharpness":[0.6,1.4]}},"rotation":{"type":"RandomRotation","kwargs":{"degrees":[-5,5]}},"translation":{"type":"RandomAffine","kwargs":{"degrees":0,"translate":[0.1,0.1]}}}' \
+  --dataset.video_backend=torchcodec \
+  --policy.use_amp=true \
+  --policy.horizon=48 \
+  --policy.n_obs_steps=2 \
+  --policy.use_rope=true \
+  --policy.use_positional_encoding=false \
+  --policy.hidden_dim=768 \
+  --policy.num_layers=8 \
+  --policy.num_heads=12 \
+  --policy.dropout=0.1 \
+  --policy.timestep_embed_dim=256 \
+  --policy.objective=diffusion \
+  --policy.optimizer_lr=3e-4 \
+  --policy.optimizer_weight_decay=0 \
+  --policy.scheduler_warmup_steps=0 \
+  --policy.vision_encoder_name=openai/clip-vit-base-patch16 \
+  --policy.image_resize_shape=[256,256] \
+  --policy.image_crop_is_random=true \
+  --policy.text_encoder_name=openai/clip-vit-base-patch16 \
+  --policy.vision_encoder_lr_multiplier=0.1 \
+  --policy.device=cuda \
+  --num_workers=8 \
+  --save_freq=4000 \
+  --log_freq=100 \
+  --steps=100000 \
+  --batch_size=320
+```
+
+Results:
+
+| LIBERO Spatial | LIBERO Object | LIBERO Goal | LIBERO 10 | Average |
+| -------------- | ------------- | ----------- | --------- | ------- |
+| 87.0           | 98.2          | 93.8        | 83.2      | 90.6    |
+
 ## References
 
 For more details on the technical implementation and architecture, see:

docs/source/policy_pi05_README.md

@@ -0,0 +1,91 @@
+# π₀.₅ (pi05)
+
+This repository contains the Hugging Face port of **π₀.₅**, adapted from [OpenPI](https://github.com/Physical-Intelligence/openpi) by the Physical Intelligence.
+It is designed as a **Vision-Language-Action model with open-world generalization**.
+
+---
+
+## Model Overview
+
+| Feature              | π₀                                                     | π₀.₅                                      |
+| -------------------- | ------------------------------------------------------ | ----------------------------------------- |
+| Time Conditioning    | Concatenates time with actions via `action_time_mlp_*` | Uses `time_mlp_*` for AdaRMS conditioning |
+| AdaRMS               | Not used                                               | Used in action expert                     |
+| Tokenizer Length     | 48 tokens                                              | 200 tokens                                |
+| Discrete State Input | False (Uses `state_proj` layer)                        | True                                      |
+| Parameter Count      | Higher (includes state embedding)                      | Lower (no state embedding)                |
+
+---
+
+## Relative Actions
+
+π₀.₅ supports training with **relative actions**, where the model learns relative offsets
+from the current robot state instead of absolute joint positions. This mirrors the
+relative-action transform in OpenPI (`DeltaActions`) and can improve performance.
+
+### How it works
+
+1. **During preprocessing**, absolute actions are converted to relative offsets:
+   `relative = action - state` (for selected joints).
+2. The relative actions are normalized using statistics computed from the relative distribution.
+3. **During postprocessing**, predicted relative actions are converted back to absolute:
+   `absolute = relative + state`.
+
+Joints listed in `relative_exclude_joints` (e.g., gripper) are kept absolute.
+
+### Configuration
+
+| Parameter                 | Type        | Default       | Description                                                      |
+| ------------------------- | ----------- | ------------- | ---------------------------------------------------------------- |
+| `use_relative_actions`    | `bool`      | `False`       | Enable relative-action training                                  |
+| `relative_exclude_joints` | `list[str]` | `["gripper"]` | Joint names to keep absolute (matched by substring)              |
+| `action_feature_names`    | `list[str]` | `None`        | Auto-populated from dataset metadata at runtime by `make_policy` |
+
+### Training example
+
+```bash
+python -m lerobot.scripts.lerobot_train \
+  --policy.type=pi05 \
+  --dataset.repo_id=your_org/your_dataset \
+  --policy.use_relative_actions=true \
+  --policy.relative_exclude_joints='["gripper"]'
+```
+
+When `use_relative_actions=true`, the training script automatically:
+
+- Computes relative action statistics from the dataset (sampled chunk-level relative actions)
+- Replaces the standard action stats with relative stats for normalization
+- Broadcasts these stats across all ranks in distributed training
+
+---
+
+## Citation
+
+If you use this work, please cite both **OpenPI** and the π₀.₅ paper:
+
+```bibtex
+@misc{openpi2024,
+  author       = {Physical Intelligence Lab},
+  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
+  year         = {2024},
+  publisher    = {GitHub},
+  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
+  license      = {Apache-2.0}
+}
+
+@misc{intelligence2025pi05visionlanguageactionmodelopenworld,
+  title        = {π₀.₅: a Vision-Language-Action Model with Open-World Generalization},
+  author       = {Physical Intelligence and Kevin Black and Noah Brown and James Darpinian and Karan Dhabalia and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Manuel Y. Galliker and Dibya Ghosh and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and James Tanner and Quan Vuong and Homer Walke and Anna Walling and Haohuan Wang and Lili Yu and Ury Zhilinsky},
+  year         = {2025},
+  eprint       = {2504.16054},
+  archivePrefix= {arXiv},
+  primaryClass = {cs.LG},
+  url          = {https://arxiv.org/abs/2504.16054},
+}
+```
+
+---
+
+## License
+
+This port follows the **Apache 2.0 License**, consistent with the original [OpenPI repository](https://github.com/Physical-Intelligence/openpi).

docs/source/policy_pi0_README.md

@@ -0,0 +1,108 @@
+# π₀ (pi0)
+
+This repository contains the Hugging Face port of **π₀**, adapted from [OpenPI](https://github.com/Physical-Intelligence/openpi) by the Physical Intelligence.
+It is designed as a **Vision-Language-Action model for general robot control**.
+
+---
+
+## Model Overview
+
+| Feature              | π₀                                                     | π₀.₅                                      |
+| -------------------- | ------------------------------------------------------ | ----------------------------------------- |
+| Time Conditioning    | Concatenates time with actions via `action_time_mlp_*` | Uses `time_mlp_*` for AdaRMS conditioning |
+| AdaRMS               | Not used                                               | Used in action expert                     |
+| Tokenizer Length     | 48 tokens                                              | 200 tokens                                |
+| Discrete State Input | False (Uses `state_proj` layer)                        | True                                      |
+| Parameter Count      | Higher (includes state embedding)                      | Lower (no state embedding)                |
+
+---
+
+## Relative Actions
+
+π₀ supports training with **relative actions**, where the model learns relative offsets
+from the current robot state instead of absolute joint positions. This mirrors the
+relative-action transform in OpenPI (`DeltaActions`) and can improve performance.
+
+### How it works
+
+1. **During preprocessing**, absolute actions are converted to relative offsets:
+   `relative = action - state` (for selected joints).
+2. The relative actions are normalized using statistics computed from the relative distribution.
+3. **During postprocessing**, predicted relative actions are converted back to absolute:
+   `absolute = relative + state`.
+
+Joints listed in `relative_exclude_joints` (e.g., gripper) are kept absolute.
+
+### Configuration
+
+| Parameter                 | Type        | Default       | Description                                                      |
+| ------------------------- | ----------- | ------------- | ---------------------------------------------------------------- |
+| `use_relative_actions`    | `bool`      | `False`       | Enable relative-action training                                  |
+| `relative_exclude_joints` | `list[str]` | `["gripper"]` | Joint names to keep absolute (matched by substring)              |
+| `action_feature_names`    | `list[str]` | `None`        | Auto-populated from dataset metadata at runtime by `make_policy` |
+
+### Training example
+
+```bash
+python -m lerobot.scripts.lerobot_train \
+  --policy.type=pi0 \
+  --dataset.repo_id=your_org/your_dataset \
+  --policy.use_relative_actions=true \
+  --policy.relative_exclude_joints='["gripper"]'
+```
+
+When `use_relative_actions=true`, the training script automatically:
+
+- Computes relative action statistics from the dataset (sampled chunk-level relative actions)
+- Replaces the standard action stats with relative stats for normalization
+- Broadcasts these stats across all ranks in distributed training
+
+### Recomputing stats for an existing dataset
+
+If you want to precompute relative action stats offline, use `recompute_stats` from
+`lerobot.datasets.dataset_tools`:
+
+```python
+from lerobot.datasets.lerobot_dataset import LeRobotDataset
+from lerobot.datasets.dataset_tools import recompute_stats
+
+dataset = LeRobotDataset("your_org/your_dataset")
+dataset = recompute_stats(
+    dataset,
+    relative_action=True,
+    relative_exclude_joints=["gripper"],
+)
+```
+
+---
+
+## Citation
+
+If you use this work, please cite both **OpenPI** and the π₀ paper:
+
+```bibtex
+@misc{openpi2024,
+  author       = {Physical Intelligence Lab},
+  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
+  year         = {2024},
+  publisher    = {GitHub},
+  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
+  license      = {Apache-2.0}
+}
+
+@misc{black2024pi0visionlanguageactionflowmodel,
+  title        = {π₀: A Vision-Language-Action Flow Model for General Robot Control},
+  author       = {Kevin Black and Noah Brown and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Lucy Xiaoyang Shi and James Tanner and Quan Vuong and Anna Walling and Haohuan Wang and Ury Zhilinsky},
+  year         = {2024},
+  eprint       = {2410.24164},
+  archivePrefix= {arXiv},
+  primaryClass = {cs.LG},
+  url          = {https://arxiv.org/abs/2410.24164},
+}
+```
+
+---
+
+## License
+
+This port follows the **Apache 2.0 License**, consistent with the original [OpenPI repository](https://github.com/Physical-Intelligence/openpi).

docs/source/policy_rtc_README.md

@@ -0,0 +1,38 @@
+# Real-Time Chunking (RTC)
+
+This module contains the LeRobot implementation of **Real-Time Chunking (RTC)**, an inference-time technique for flow-matching based policies.
+
+**Note**: RTC is not a policy itself, but rather an inference enhancement that works with flow-matching based policies including [π₀](../pi0/), [π₀.₅](../pi05/), and [SmolVLA](../smolvla/).
+
+---
+
+## Citation
+
+If you use Real-Time Chunking in your work, please cite:
+
+```bibtex
+@misc{openpi2024,
+  author       = {Physical Intelligence Lab},
+  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
+  year         = {2024},
+  publisher    = {GitHub},
+  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
+  license      = {Apache-2.0}
+}
+
+@misc{black2025realtimeexecutionactionchunking,
+      title={Real-Time Execution of Action Chunking Flow Policies},
+      author={Kevin Black and Manuel Y. Galliker and Sergey Levine},
+      year={2025},
+      eprint={2506.07339},
+      archivePrefix={arXiv},
+      primaryClass={cs.RO},
+      url={https://arxiv.org/abs/2506.07339},
+}
+```
+
+---
+
+## License
+
+This implementation follows the **Apache 2.0 License**, consistent with the LeRobot project.

docs/source/policy_sarm_README.md

@@ -0,0 +1,14 @@
+## Paper
+
+https://arxiv.org/abs/2509.25358
+
+## Citation
+
+```bibtex
+@article{chen2025sarm,
+  title={SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation},
+  author={Chen, Qianzhong and Yu, Justin and Schwager, Mac and Abbeel, Pieter and Shentu, Yide and Wu, Philipp},
+  journal={arXiv preprint arXiv:2509.25358},
+  year={2025}
+}
+```

pyproject.toml

@@ -25,7 +25,7 @@ discord = "https://discord.gg/s3KuuzsPFb"
 
 [project]
 name = "lerobot"
-version = "0.5.1"
+version = "0.5.2"
 description = "🤗 LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch"
 dynamic = ["readme"]
 license = { text = "Apache-2.0" }
@@ -71,9 +71,9 @@ dependencies = [
     "cmake>=3.29.0.1,<4.2.0",
     "packaging>=24.2,<26.0",
 
-    "torch>=2.2.1,<2.11.0",
+    "torch>=2.7,<2.11.0",
-    "torchcodec>=0.2.1,<0.11.0; 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')",
+    "torchcodec>=0.3.0,<0.11.0; 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')", # NOTE: Windows support starts at version 0.7 (needs torch==2.8), ffmpeg>=8 support starts at version 0.8.1 (needs torch==2.9), system-wide ffmpeg support starts at version 0.10 (needs torch==2.10).
-    "torchvision>=0.21.0,<0.26.0",
+    "torchvision>=0.22.0,<0.26.0",
 
     "einops>=0.8.0,<0.9.0",
     "opencv-python-headless>=4.9.0,<4.14.0",

src/lerobot/configs/default.py

@@ -67,8 +67,7 @@ class EvalConfig:
     # `batch_size` specifies the number of environments to use in a gym.vector.VectorEnv.
     batch_size: int = 50
     # `use_async_envs` specifies whether to use asynchronous environments (multiprocessing).
-    # Defaults to True; automatically downgraded to SyncVectorEnv when batch_size=1.
+    use_async_envs: bool = False
-    use_async_envs: bool = True
 
     def __post_init__(self) -> None:
         if self.batch_size > self.n_episodes:

src/lerobot/datasets/lerobot_dataset.py

@@ -151,9 +151,11 @@ class LeRobotDataset(torch.utils.data.Dataset):
                 ``$HF_LEROBOT_HOME/hub``.
             episodes (list[int] | None, optional): If specified, this will only load episodes specified by
                 their episode_index in this list. Defaults to None.
-            image_transforms (Callable | None, optional): You can pass standard v2 image transforms from
+            image_transforms (Callable | None, optional):
-                torchvision.transforms.v2 here which will be applied to visual modalities (whether they come
+                Transform applied to visual modalities inside `__getitem__` after image decoding / tensor
-                from videos or images). Defaults to None.
+                conversion. This works for both image-backed and video-backed observations and can later be
+                updated with `set_image_transforms()` or cleared with `clear_image_transforms()`.
+                Defaults to None.
             delta_timestamps (dict[list[float]] | None, optional): _description_. Defaults to None.
             tolerance_s (float, optional): Tolerance in seconds used to ensure data timestamps are actually in
                 sync with the fps value. It is used at the init of the dataset to make sure that each
@@ -192,7 +194,8 @@ class LeRobotDataset(torch.utils.data.Dataset):
         super().__init__()
         self.repo_id = repo_id
         self._requested_root = Path(root) if root else None
-        self.image_transforms = image_transforms
+        self.reader = None
+        self.set_image_transforms(image_transforms)
         self.delta_timestamps = delta_timestamps
         self.episodes = episodes
         self.tolerance_s = tolerance_s
@@ -475,6 +478,18 @@ class LeRobotDataset(torch.utils.data.Dataset):
             f"}})"
         )
 
+    def set_image_transforms(self, image_transforms: Callable | None) -> None:
+        """Replace the transform applied to visual observations."""
+        if image_transforms is not None and not callable(image_transforms):
+            raise TypeError("image_transforms must be callable or None.")
+        self.image_transforms = image_transforms
+        if self.reader is not None:
+            self.reader._image_transforms = image_transforms
+
+    def clear_image_transforms(self) -> None:
+        """Remove the transform applied to visual observations."""
+        self.set_image_transforms(None)
+
     # ── Hub methods (stay on facade) ──────────────────────────────────
 
     def push_to_hub(

src/lerobot/datasets/multi_dataset.py

@@ -89,12 +89,24 @@ class MultiLeRobotDataset(torch.utils.data.Dataset):
                 )
                 self.disabled_features.update(extra_keys)
 
-        self.image_transforms = image_transforms
         self.delta_timestamps = delta_timestamps
         # TODO(rcadene, aliberts): We should not perform this aggregation for datasets
         # with multiple robots of different ranges. Instead we should have one normalization
         # per robot.
         self.stats = aggregate_stats([dataset.meta.stats for dataset in self._datasets])
+        self.set_image_transforms(image_transforms)
+
+    def set_image_transforms(self, image_transforms: Callable | None) -> None:
+        """Replace the transform for this dataset and its children."""
+        if image_transforms is not None and not callable(image_transforms):
+            raise TypeError("image_transforms must be callable or None.")
+        self.image_transforms = image_transforms
+        for dataset in getattr(self, "_datasets", []):
+            dataset.set_image_transforms(self.image_transforms)
+
+    def clear_image_transforms(self) -> None:
+        """Remove the transform from this dataset and its children."""
+        self.set_image_transforms(None)
 
     @property
     def repo_id_to_index(self):

src/lerobot/envs/configs.py

@@ -75,14 +75,13 @@ class EnvConfig(draccus.ChoiceRegistry, abc.ABC):
     def create_envs(
         self,
         n_envs: int,
-        use_async_envs: bool = True,
+        use_async_envs: bool = False,
     ) -> dict[str, dict[int, gym.vector.VectorEnv]]:
         """Create {suite: {task_id: VectorEnv}}.
 
         Default: single-task env via gym.make(). Multi-task benchmarks override.
-        AsyncVectorEnv is the default for n_envs > 1; auto-downgraded to Sync for n_envs=1.
         """
-        env_cls = gym.vector.AsyncVectorEnv if (use_async_envs and n_envs > 1) else gym.vector.SyncVectorEnv
+        env_cls = gym.vector.AsyncVectorEnv if use_async_envs else gym.vector.SyncVectorEnv
 
         if self.gym_id not in gym_registry:
             print(f"gym id '{self.gym_id}' not found, attempting to import '{self.package_name}'...")
@@ -102,7 +101,12 @@ class EnvConfig(draccus.ChoiceRegistry, abc.ABC):
         def _make_one():
             return gym.make(self.gym_id, disable_env_checker=self.disable_env_checker, **self.gym_kwargs)
 
-        vec = env_cls([_make_one for _ in range(n_envs)], autoreset_mode=gym.vector.AutoresetMode.SAME_STEP)
+        try:
+            from gymnasium.vector import AutoresetMode
+
+            vec = env_cls([_make_one for _ in range(n_envs)], autoreset_mode=AutoresetMode.SAME_STEP)
+        except ImportError:
+            vec = env_cls([_make_one for _ in range(n_envs)])
         return {self.type: {0: vec}}
 
     def get_env_processors(self):
@@ -382,6 +386,12 @@ class LiberoEnv(EnvConfig):
         else:
             raise ValueError(f"Unsupported obs_type: {self.obs_type}")
 
+        if self.camera_name_mapping is not None:
+            mapped_agentview = self.camera_name_mapping.get("agentview_image", "image")
+            mapped_eye_in_hand = self.camera_name_mapping.get("robot0_eye_in_hand_image", "image2")
+            self.features_map[LIBERO_KEY_PIXELS_AGENTVIEW] = f"{OBS_IMAGES}.{mapped_agentview}"
+            self.features_map[LIBERO_KEY_PIXELS_EYE_IN_HAND] = f"{OBS_IMAGES}.{mapped_eye_in_hand}"
+
     @property
     def gym_kwargs(self) -> dict:
         kwargs: dict[str, Any] = {"obs_type": self.obs_type, "render_mode": self.render_mode}
@@ -389,12 +399,12 @@ class LiberoEnv(EnvConfig):
             kwargs["task_ids"] = self.task_ids
         return kwargs
 
-    def create_envs(self, n_envs: int, use_async_envs: bool = True):
+    def create_envs(self, n_envs: int, use_async_envs: bool = False):
         from lerobot.envs.libero import create_libero_envs
 
         if self.task is None:
             raise ValueError("LiberoEnv requires a task to be specified")
-        env_cls = gym.vector.AsyncVectorEnv if (use_async_envs and n_envs > 1) else gym.vector.SyncVectorEnv
+        env_cls = gym.vector.AsyncVectorEnv if use_async_envs else gym.vector.SyncVectorEnv
         return create_libero_envs(
             task=self.task,
             n_envs=n_envs,
@@ -404,6 +414,7 @@ class LiberoEnv(EnvConfig):
             env_cls=env_cls,
             control_mode=self.control_mode,
             episode_length=self.episode_length,
+            camera_name_mapping=self.camera_name_mapping,
         )
 
     def get_env_processors(self):
@@ -457,12 +468,12 @@ class MetaworldEnv(EnvConfig):
             "render_mode": self.render_mode,
         }
 
-    def create_envs(self, n_envs: int, use_async_envs: bool = True):
+    def create_envs(self, n_envs: int, use_async_envs: bool = False):
         from lerobot.envs.metaworld import create_metaworld_envs
 
         if self.task is None:
             raise ValueError("MetaWorld requires a task to be specified")
-        env_cls = gym.vector.AsyncVectorEnv if (use_async_envs and n_envs > 1) else gym.vector.SyncVectorEnv
+        env_cls = gym.vector.AsyncVectorEnv if use_async_envs else gym.vector.SyncVectorEnv
         return create_metaworld_envs(
             task=self.task,
             n_envs=n_envs,

src/lerobot/envs/factory.py

@@ -58,7 +58,7 @@ def make_env_pre_post_processors(
 def make_env(
     cfg: EnvConfig | str,
     n_envs: int = 1,
-    use_async_envs: bool = True,
+    use_async_envs: bool = False,
     hub_cache_dir: str | None = None,
     trust_remote_code: bool = False,
 ) -> dict[str, dict[int, gym.vector.VectorEnv]]:

src/lerobot/envs/libero.py

@@ -150,17 +150,7 @@ class LiberoEnv(gym.Env):
 
         self.init_state_id = self.episode_index  # tie each sub-env to a fixed init state
 
-        # Extract task metadata without allocating GPU resources (safe before fork).
+        self._env = self._make_envs_task(task_suite, self.task_id)
-        task = task_suite.get_task(task_id)
-        self.task = task.name
-        self.task_description = task.language
-        self._task_bddl_file = os.path.join(
-            get_libero_path("bddl_files"), task.problem_folder, task.bddl_file
-        )
-        self._env: OffScreenRenderEnv | None = (
-            None  # deferred — created on first reset() inside the worker subprocess
-        )
-
         default_steps = 500
         self._max_episode_steps = (
             TASK_SUITE_MAX_STEPS.get(task_suite_name, default_steps)
@@ -231,32 +221,29 @@ class LiberoEnv(gym.Env):
             low=ACTION_LOW, high=ACTION_HIGH, shape=(ACTION_DIM,), dtype=np.float32
         )
 
-    def _ensure_env(self) -> None:
-        """Create the underlying OffScreenRenderEnv on first use.
-
-        Called inside the worker subprocess after fork(), so each worker gets
-        its own clean EGL context rather than inheriting a stale one from the
-        parent process (which causes EGL_BAD_CONTEXT crashes with AsyncVectorEnv).
-        """
-        if self._env is not None:
-            return
-        env = OffScreenRenderEnv(
-            bddl_file_name=self._task_bddl_file,
-            camera_heights=self.observation_height,
-            camera_widths=self.observation_width,
-        )
-        env.reset()
-        self._env = env
-
     def render(self):
-        self._ensure_env()
         raw_obs = self._env.env._get_observations()
-        image = self._format_raw_obs(raw_obs)["pixels"]["image"]
+        pixels = self._format_raw_obs(raw_obs)["pixels"]
+        image = next(iter(pixels.values()))
         image = image[::-1, ::-1]  # flip both H and W for visualization
         return image
 
+    def _make_envs_task(self, task_suite: Any, task_id: int = 0):
+        task = task_suite.get_task(task_id)
+        self.task = task.name
+        self.task_description = task.language
+        task_bddl_file = os.path.join(get_libero_path("bddl_files"), task.problem_folder, task.bddl_file)
+
+        env_args = {
+            "bddl_file_name": task_bddl_file,
+            "camera_heights": self.observation_height,
+            "camera_widths": self.observation_width,
+        }
+        env = OffScreenRenderEnv(**env_args)
+        env.reset()
+        return env
+
     def _format_raw_obs(self, raw_obs: RobotObservation) -> RobotObservation:
-        assert self._env is not None, "_format_raw_obs called before _ensure_env()"
         images = {}
         for camera_name in self.camera_name:
             image = raw_obs[camera_name]
@@ -308,7 +295,6 @@ class LiberoEnv(gym.Env):
         )
 
     def reset(self, seed=None, **kwargs):
-        self._ensure_env()
         super().reset(seed=seed)
         self._env.seed(seed)
         raw_obs = self._env.reset()
@@ -335,8 +321,6 @@ class LiberoEnv(gym.Env):
         return observation, info
 
     def step(self, action: np.ndarray) -> tuple[RobotObservation, float, bool, bool, dict[str, Any]]:
-        self._ensure_env()
-        assert self._env is not None
         if action.ndim != 1:
             raise ValueError(
                 f"Expected action to be 1-D (shape (action_dim,)), "
@@ -356,19 +340,12 @@ class LiberoEnv(gym.Env):
         )
         observation = self._format_raw_obs(raw_obs)
         if terminated:
-            info["final_info"] = {
-                "task": self.task,
-                "task_id": self.task_id,
-                "done": bool(done),
-                "is_success": bool(is_success),
-            }
             self.reset()
         truncated = False
         return observation, reward, terminated, truncated, info
 
     def close(self):
-        if self._env is not None:
+        self._env.close()
-            self._env.close()
 
 
 def _make_env_fns(
@@ -382,6 +359,7 @@ def _make_env_fns(
     init_states: bool,
     gym_kwargs: Mapping[str, Any],
     control_mode: str,
+    camera_name_mapping: dict[str, str] | None = None,
 ) -> list[Callable[[], LiberoEnv]]:
     """Build n_envs factory callables for a single (suite, task_id)."""
 
@@ -397,6 +375,7 @@ def _make_env_fns(
             episode_index=episode_index,
             n_envs=n_envs,
             control_mode=control_mode,
+            camera_name_mapping=camera_name_mapping,
             **local_kwargs,
         )
 
@@ -418,6 +397,7 @@ def create_libero_envs(
     env_cls: Callable[[Sequence[Callable[[], Any]]], Any] | None = None,
     control_mode: str = "relative",
     episode_length: int | None = None,
+    camera_name_mapping: dict[str, str] | None = None,
 ) -> dict[str, dict[int, Any]]:
     """
     Create vectorized LIBERO environments with a consistent return shape.
@@ -467,6 +447,7 @@ def create_libero_envs(
                 init_states=init_states,
                 gym_kwargs=gym_kwargs,
                 control_mode=control_mode,
+                camera_name_mapping=camera_name_mapping,
             )
             out[suite_name][tid] = env_cls(fns)
             print(f"Built vec env | suite={suite_name} | task_id={tid} | n_envs={n_envs}")

src/lerobot/envs/metaworld.py

@@ -97,9 +97,8 @@ class MetaworldEnv(gym.Env):
         self.visualization_height = visualization_height
         self.camera_name = camera_name
 
-        self._env_name = self.task  # already stripped of "metaworld-" prefix above
+        self._env = self._make_envs_task(self.task)
-        self._env = None  # deferred — created on first reset() inside the worker subprocess
+        self._max_episode_steps = self._env.max_path_length
-        self._max_episode_steps = 500  # MT1 environments always have max_path_length=500
         self.task_description = TASK_DESCRIPTIONS[self.task]
 
         self.expert_policy = TASK_POLICY_MAPPING[self.task]()
@@ -137,24 +136,6 @@ class MetaworldEnv(gym.Env):
 
         self.action_space = spaces.Box(low=-1, high=1, shape=(ACTION_DIM,), dtype=np.float32)
 
-    def _ensure_env(self) -> None:
-        """Create the underlying MetaWorld env on first use.
-
-        Called inside the worker subprocess after fork(), so each worker gets
-        its own clean rendering context rather than inheriting a stale one from
-        the parent process (which causes crashes with AsyncVectorEnv).
-        """
-        if self._env is not None:
-            return
-        mt1 = metaworld.MT1(self._env_name, seed=42)
-        env = mt1.train_classes[self._env_name](render_mode="rgb_array", camera_name=self.camera_name)
-        env.set_task(mt1.train_tasks[0])
-        if self.camera_name == "corner2":
-            env.model.cam_pos[2] = [0.75, 0.075, 0.7]
-        env.reset()
-        env._freeze_rand_vec = False  # otherwise no randomization
-        self._env = env
-
     def render(self) -> np.ndarray:
         """
         Render the current environment frame.
@@ -162,13 +143,26 @@ class MetaworldEnv(gym.Env):
         Returns:
             np.ndarray: The rendered RGB image from the environment.
         """
-        self._ensure_env()
         image = self._env.render()
         if self.camera_name == "corner2":
             # Images from this camera are flipped — correct them
             image = np.flip(image, (0, 1))
         return image
 
+    def _make_envs_task(self, env_name: str):
+        mt1 = metaworld.MT1(env_name, seed=42)
+        env = mt1.train_classes[env_name](render_mode="rgb_array", camera_name=self.camera_name)
+        env.set_task(mt1.train_tasks[0])
+        if self.camera_name == "corner2":
+            env.model.cam_pos[2] = [
+                0.75,
+                0.075,
+                0.7,
+            ]  # corner2 position, similar to https://arxiv.org/pdf/2206.14244
+        env.reset()
+        env._freeze_rand_vec = False  # otherwise no randomization
+        return env
+
     def _format_raw_obs(self, raw_obs: np.ndarray) -> RobotObservation:
         image = None
         if self._env is not None:
@@ -215,7 +209,6 @@ class MetaworldEnv(gym.Env):
             observation (RobotObservation): The initial formatted observation.
             info (Dict[str, Any]): Additional info about the reset state.
         """
-        self._ensure_env()
         super().reset(seed=seed)
 
         raw_obs, info = self._env.reset(seed=seed)
@@ -239,7 +232,6 @@ class MetaworldEnv(gym.Env):
             truncated (bool): Whether the episode was truncated due to a time limit.
             info (Dict[str, Any]): Additional environment info.
         """
-        self._ensure_env()
         if action.ndim != 1:
             raise ValueError(
                 f"Expected action to be 1-D (shape (action_dim,)), "
@@ -271,8 +263,7 @@ class MetaworldEnv(gym.Env):
         return observation, reward, terminated, truncated, info
 
     def close(self):
-        if self._env is not None:
+        self._env.close()
-            self._env.close()
 
 
 # ---- Main API ----------------------------------------------------------------

src/lerobot/policies/multi_task_dit/README.md

@@ -1,37 +0,0 @@
-# Multitask DiT Policy
-
-## Citation
-
-If you use this work, please cite the following works:
-
-```bibtex
-@misc{jones2025multitaskditpolicy,
-  author = {Bryson Jones},
-  title = {Dissecting and Open-Sourcing Multitask Diffusion Transformer Policy},
-  year = {2025},
-  url = {https://brysonkjones.substack.com/p/dissecting-and-open-sourcing-multitask-diffusion-transformer-policy},
-  note = {Blog post}
-}
-```
-
-```bibtex
-@misc{trilbmteam2025carefulexaminationlargebehaviormodels,
-  author       = {TRI LBM Team},
-  title        = {A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation},
-  year         = {2025},
-  eprint       = {arXiv:2507.05331},
-  archivePrefix = {arXiv},
-  primaryClass = {cs.RO},
-  url          = {https://arxiv.org/abs/2507.05331}
-}
-```
-
-```bibtex
-@misc{bostondynamics2025largebehaviormodelsatlas,
-  author       = {Boston Dynamics and TRI Research Team},
-  title        = {Large Behavior Models and Atlas Find New Footing},
-  year         = {2025},
-  url          = {https://bostondynamics.com/blog/large-behavior-models-atlas-find-new-footing/},
-  note         = {Blog post}
-}
-```

src/lerobot/policies/multi_task_dit/README.md

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

src/lerobot/policies/pi0/README.md

@@ -1,108 +0,0 @@
-# π₀ (pi0)
-
-This repository contains the Hugging Face port of **π₀**, adapted from [OpenPI](https://github.com/Physical-Intelligence/openpi) by the Physical Intelligence.
-It is designed as a **Vision-Language-Action model for general robot control**.
-
----
-
-## Model Overview
-
-| Feature              | π₀                                                     | π₀.₅                                      |
-| -------------------- | ------------------------------------------------------ | ----------------------------------------- |
-| Time Conditioning    | Concatenates time with actions via `action_time_mlp_*` | Uses `time_mlp_*` for AdaRMS conditioning |
-| AdaRMS               | Not used                                               | Used in action expert                     |
-| Tokenizer Length     | 48 tokens                                              | 200 tokens                                |
-| Discrete State Input | False (Uses `state_proj` layer)                        | True                                      |
-| Parameter Count      | Higher (includes state embedding)                      | Lower (no state embedding)                |
-
----
-
-## Relative Actions
-
-π₀ supports training with **relative actions**, where the model learns relative offsets
-from the current robot state instead of absolute joint positions. This mirrors the
-relative-action transform in OpenPI (`DeltaActions`) and can improve performance.
-
-### How it works
-
-1. **During preprocessing**, absolute actions are converted to relative offsets:
-   `relative = action - state` (for selected joints).
-2. The relative actions are normalized using statistics computed from the relative distribution.
-3. **During postprocessing**, predicted relative actions are converted back to absolute:
-   `absolute = relative + state`.
-
-Joints listed in `relative_exclude_joints` (e.g., gripper) are kept absolute.
-
-### Configuration
-
-| Parameter                 | Type        | Default       | Description                                                      |
-| ------------------------- | ----------- | ------------- | ---------------------------------------------------------------- |
-| `use_relative_actions`    | `bool`      | `False`       | Enable relative-action training                                  |
-| `relative_exclude_joints` | `list[str]` | `["gripper"]` | Joint names to keep absolute (matched by substring)              |
-| `action_feature_names`    | `list[str]` | `None`        | Auto-populated from dataset metadata at runtime by `make_policy` |
-
-### Training example
-
-```bash
-python -m lerobot.scripts.lerobot_train \
-  --policy.type=pi0 \
-  --dataset.repo_id=your_org/your_dataset \
-  --policy.use_relative_actions=true \
-  --policy.relative_exclude_joints='["gripper"]'
-```
-
-When `use_relative_actions=true`, the training script automatically:
-
-- Computes relative action statistics from the dataset (sampled chunk-level relative actions)
-- Replaces the standard action stats with relative stats for normalization
-- Broadcasts these stats across all ranks in distributed training
-
-### Recomputing stats for an existing dataset
-
-If you want to precompute relative action stats offline, use `recompute_stats` from
-`lerobot.datasets.dataset_tools`:
-
-```python
-from lerobot.datasets.lerobot_dataset import LeRobotDataset
-from lerobot.datasets.dataset_tools import recompute_stats
-
-dataset = LeRobotDataset("your_org/your_dataset")
-dataset = recompute_stats(
-    dataset,
-    relative_action=True,
-    relative_exclude_joints=["gripper"],
-)
-```
-
----
-
-## Citation
-
-If you use this work, please cite both **OpenPI** and the π₀ paper:
-
-```bibtex
-@misc{openpi2024,
-  author       = {Physical Intelligence Lab},
-  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
-  year         = {2024},
-  publisher    = {GitHub},
-  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
-  license      = {Apache-2.0}
-}
-
-@misc{black2024pi0visionlanguageactionflowmodel,
-  title        = {π₀: A Vision-Language-Action Flow Model for General Robot Control},
-  author       = {Kevin Black and Noah Brown and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Lucy Xiaoyang Shi and James Tanner and Quan Vuong and Anna Walling and Haohuan Wang and Ury Zhilinsky},
-  year         = {2024},
-  eprint       = {2410.24164},
-  archivePrefix= {arXiv},
-  primaryClass = {cs.LG},
-  url          = {https://arxiv.org/abs/2410.24164},
-}
-```
-
----
-
-## License
-
-This port follows the **Apache 2.0 License**, consistent with the original [OpenPI repository](https://github.com/Physical-Intelligence/openpi).

src/lerobot/policies/pi0/README.md

@@ -0,0 +1 @@
+../../../../docs/source/policy_pi0_README.md

src/lerobot/policies/pi05/README.md

@@ -1,91 +0,0 @@
-# π₀.₅ (pi05)
-
-This repository contains the Hugging Face port of **π₀.₅**, adapted from [OpenPI](https://github.com/Physical-Intelligence/openpi) by the Physical Intelligence.
-It is designed as a **Vision-Language-Action model with open-world generalization**.
-
----
-
-## Model Overview
-
-| Feature              | π₀                                                     | π₀.₅                                      |
-| -------------------- | ------------------------------------------------------ | ----------------------------------------- |
-| Time Conditioning    | Concatenates time with actions via `action_time_mlp_*` | Uses `time_mlp_*` for AdaRMS conditioning |
-| AdaRMS               | Not used                                               | Used in action expert                     |
-| Tokenizer Length     | 48 tokens                                              | 200 tokens                                |
-| Discrete State Input | False (Uses `state_proj` layer)                        | True                                      |
-| Parameter Count      | Higher (includes state embedding)                      | Lower (no state embedding)                |
-
----
-
-## Relative Actions
-
-π₀.₅ supports training with **relative actions**, where the model learns relative offsets
-from the current robot state instead of absolute joint positions. This mirrors the
-relative-action transform in OpenPI (`DeltaActions`) and can improve performance.
-
-### How it works
-
-1. **During preprocessing**, absolute actions are converted to relative offsets:
-   `relative = action - state` (for selected joints).
-2. The relative actions are normalized using statistics computed from the relative distribution.
-3. **During postprocessing**, predicted relative actions are converted back to absolute:
-   `absolute = relative + state`.
-
-Joints listed in `relative_exclude_joints` (e.g., gripper) are kept absolute.
-
-### Configuration
-
-| Parameter                 | Type        | Default       | Description                                                      |
-| ------------------------- | ----------- | ------------- | ---------------------------------------------------------------- |
-| `use_relative_actions`    | `bool`      | `False`       | Enable relative-action training                                  |
-| `relative_exclude_joints` | `list[str]` | `["gripper"]` | Joint names to keep absolute (matched by substring)              |
-| `action_feature_names`    | `list[str]` | `None`        | Auto-populated from dataset metadata at runtime by `make_policy` |
-
-### Training example
-
-```bash
-python -m lerobot.scripts.lerobot_train \
-  --policy.type=pi05 \
-  --dataset.repo_id=your_org/your_dataset \
-  --policy.use_relative_actions=true \
-  --policy.relative_exclude_joints='["gripper"]'
-```
-
-When `use_relative_actions=true`, the training script automatically:
-
-- Computes relative action statistics from the dataset (sampled chunk-level relative actions)
-- Replaces the standard action stats with relative stats for normalization
-- Broadcasts these stats across all ranks in distributed training
-
----
-
-## Citation
-
-If you use this work, please cite both **OpenPI** and the π₀.₅ paper:
-
-```bibtex
-@misc{openpi2024,
-  author       = {Physical Intelligence Lab},
-  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
-  year         = {2024},
-  publisher    = {GitHub},
-  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
-  license      = {Apache-2.0}
-}
-
-@misc{intelligence2025pi05visionlanguageactionmodelopenworld,
-  title        = {π₀.₅: a Vision-Language-Action Model with Open-World Generalization},
-  author       = {Physical Intelligence and Kevin Black and Noah Brown and James Darpinian and Karan Dhabalia and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Manuel Y. Galliker and Dibya Ghosh and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and James Tanner and Quan Vuong and Homer Walke and Anna Walling and Haohuan Wang and Lili Yu and Ury Zhilinsky},
-  year         = {2025},
-  eprint       = {2504.16054},
-  archivePrefix= {arXiv},
-  primaryClass = {cs.LG},
-  url          = {https://arxiv.org/abs/2504.16054},
-}
-```
-
----
-
-## License
-
-This port follows the **Apache 2.0 License**, consistent with the original [OpenPI repository](https://github.com/Physical-Intelligence/openpi).

src/lerobot/policies/pi05/README.md

@@ -0,0 +1 @@
+../../../../docs/source/policy_pi05_README.md

src/lerobot/policies/rtc/README.md

@@ -1,38 +0,0 @@
-# Real-Time Chunking (RTC)
-
-This module contains the LeRobot implementation of **Real-Time Chunking (RTC)**, an inference-time technique for flow-matching based policies.
-
-**Note**: RTC is not a policy itself, but rather an inference enhancement that works with flow-matching based policies including [π₀](../pi0/), [π₀.₅](../pi05/), and [SmolVLA](../smolvla/).
-
----
-
-## Citation
-
-If you use Real-Time Chunking in your work, please cite:
-
-```bibtex
-@misc{openpi2024,
-  author       = {Physical Intelligence Lab},
-  title        = {OpenPI: PyTorch Implementation of π0 and π0.5 Policies},
-  year         = {2024},
-  publisher    = {GitHub},
-  howpublished = {\url{https://github.com/Physical-Intelligence/openpi}},
-  license      = {Apache-2.0}
-}
-
-@misc{black2025realtimeexecutionactionchunking,
-      title={Real-Time Execution of Action Chunking Flow Policies},
-      author={Kevin Black and Manuel Y. Galliker and Sergey Levine},
-      year={2025},
-      eprint={2506.07339},
-      archivePrefix={arXiv},
-      primaryClass={cs.RO},
-      url={https://arxiv.org/abs/2506.07339},
-}
-```
-
----
-
-## License
-
-This implementation follows the **Apache 2.0 License**, consistent with the LeRobot project.

src/lerobot/policies/rtc/README.md

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

src/lerobot/policies/sarm/README.md

@@ -1,14 +0,0 @@
-## Paper
-
-https://arxiv.org/abs/2509.25358
-
-## Citation
-
-```bibtex
-@article{chen2025sarm,
-  title={SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation},
-  author={Chen, Qianzhong and Yu, Justin and Schwager, Mac and Abbeel, Pieter and Shentu, Yide and Wu, Philipp},
-  journal={arXiv preprint arXiv:2509.25358},
-  year={2025}
-}
-```

src/lerobot/policies/sarm/README.md

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

src/lerobot/scripts/lerobot_eval.py

@@ -47,7 +47,6 @@ You can learn about the CLI options for this script in the `EvalPipelineConfig`
 """
 
 import concurrent.futures as cf
-import copy
 import json
 import logging
 import threading
@@ -57,6 +56,7 @@ from collections.abc import Callable
 from contextlib import nullcontext
 from copy import deepcopy
 from dataclasses import asdict
+from functools import partial
 from pathlib import Path
 from pprint import pformat
 from typing import Any, TypedDict
@@ -73,6 +73,7 @@ from lerobot.configs import parser
 from lerobot.configs.eval import EvalPipelineConfig
 from lerobot.envs.factory import make_env, make_env_pre_post_processors
 from lerobot.envs.utils import (
+    add_envs_task,
     check_env_attributes_and_types,
     close_envs,
     preprocess_observation,
@@ -165,9 +166,9 @@ def rollout(
         if return_observations:
             all_observations.append(deepcopy(observation))
 
-        # Infer "task" from sub-environments.
+        # Infer "task" from attributes of environments.
-        # env.call() works with both SyncVectorEnv and AsyncVectorEnv.
+        # TODO: works with SyncVectorEnv but not AsyncVectorEnv
-        observation["task"] = env.call("task")
+        observation = add_envs_task(env, observation)
 
         # Apply environment-specific preprocessing (e.g., LiberoProcessorStep for LIBERO)
         observation = env_preprocessor(observation)
@@ -200,6 +201,11 @@ def rollout(
                     "You're likely using an older version of gymnasium (< 1.0). Please upgrade."
                 )
             successes = final_info["is_success"].tolist()
+        elif "is_success" in info:
+            is_success = info["is_success"]
+            successes = (
+                is_success.tolist() if hasattr(is_success, "tolist") else [bool(is_success)] * env.num_envs
+            )
         else:
             successes = [False] * env.num_envs
 
@@ -733,48 +739,34 @@ def eval_policy_all(
             group_acc[group]["video_paths"].extend(paths)
             overall["video_paths"].extend(paths)
 
-    def _make_thread_policy(p: PreTrainedPolicy) -> PreTrainedPolicy:
-        """Shallow copy sharing weight tensors, with independent per-thread state.
-
-        copy.copy() gives a new Python object whose _parameters dict is a shared
-        reference (same tensor storage, zero extra VRAM). reset() then rebinds
-        mutable state (action queues etc.) to fresh per-thread objects.
-
-        Note: does NOT work for ACT with temporal_ensemble_coeff — that policy's
-        reset() mutates a shared sub-object. Use max_parallel_tasks=1 for that config.
-        """
-        thread_p = copy.copy(p)
-        thread_p.reset()
-        return thread_p
-
     # Choose runner (sequential vs threaded)
-    _runner_kwargs = {
+    task_runner = partial(
-        "env_preprocessor": env_preprocessor,
+        run_one,
-        "env_postprocessor": env_postprocessor,
+        policy=policy,
-        "preprocessor": preprocessor,
+        env_preprocessor=env_preprocessor,
-        "postprocessor": postprocessor,
+        env_postprocessor=env_postprocessor,
-        "n_episodes": n_episodes,
+        preprocessor=preprocessor,
-        "max_episodes_rendered": max_episodes_rendered,
+        postprocessor=postprocessor,
-        "videos_dir": videos_dir,
+        n_episodes=n_episodes,
-        "return_episode_data": return_episode_data,
+        max_episodes_rendered=max_episodes_rendered,
-        "start_seed": start_seed,
+        videos_dir=videos_dir,
-    }
+        return_episode_data=return_episode_data,
+        start_seed=start_seed,
+    )
 
     if max_parallel_tasks <= 1:
         # sequential path (single accumulator path on the main thread)
         # NOTE: keeping a single-threaded accumulator avoids concurrent list appends or locks
         for task_group, task_id, env in tasks:
-            tg, tid, metrics = run_one(task_group, task_id, env, policy=policy, **_runner_kwargs)
+            tg, tid, metrics = task_runner(task_group, task_id, env)
             _accumulate_to(tg, metrics)
             per_task_infos.append({"task_group": tg, "task_id": tid, "metrics": metrics})
     else:
-        # threaded path: each thread gets a shallow policy copy (shared weights, independent state)
+        # threaded path: submit all tasks, consume completions on main thread and accumulate there
         with cf.ThreadPoolExecutor(max_workers=max_parallel_tasks) as executor:
             fut2meta = {}
             for task_group, task_id, env in tasks:
-                fut = executor.submit(
+                fut = executor.submit(task_runner, task_group, task_id, env)
-                    run_one, task_group, task_id, env, policy=_make_thread_policy(policy), **_runner_kwargs
-                )
                 fut2meta[fut] = (task_group, task_id)
             for fut in cf.as_completed(fut2meta):
                 tg, tid, metrics = fut.result()

src/lerobot/scripts/lerobot_record.py

@@ -421,6 +421,7 @@ def record_loop(
                 act_processed_policy: RobotAction = make_robot_action(action_values, dataset.features)
                 # Applies a pipeline to the action, default is IdentityProcessor
                 robot_action_to_send = robot_action_processor((act_processed_policy, obs))
+                action_values = robot_action_to_send
 
         elif policy is None and isinstance(teleop, Teleoperator):
             act = teleop.get_action()

tests/datasets/test_datasets.py

@@ -24,6 +24,7 @@ import torch
 from huggingface_hub import HfApi
 from PIL import Image
 from safetensors.torch import load_file
+from torchvision.transforms import v2
 
 import lerobot
 from lerobot.configs.default import DatasetConfig
@@ -34,6 +35,7 @@ from lerobot.datasets.image_writer import image_array_to_pil_image
 from lerobot.datasets.io_utils import hf_transform_to_torch
 from lerobot.datasets.lerobot_dataset import LeRobotDataset
 from lerobot.datasets.multi_dataset import MultiLeRobotDataset
+from lerobot.datasets.transforms import ImageTransforms, ImageTransformsConfig
 from lerobot.datasets.utils import (
     DEFAULT_CHUNK_SIZE,
     DEFAULT_DATA_FILE_SIZE_IN_MB,
@@ -355,6 +357,62 @@ def test_add_frame_image_pil(image_dataset):
     assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
 
 
+def test_set_image_transforms_applies_transparently(image_dataset):
+    dataset = image_dataset
+    dataset.add_frame({"image": np.random.rand(*DUMMY_CHW), "task": "Dummy task"})
+    dataset.save_episode()
+    dataset.finalize()
+
+    dataset.set_image_transforms(v2.Resize((224, 224)))
+    assert dataset[0]["image"].shape == torch.Size((3, 224, 224))
+
+    dataset.set_image_transforms(v2.Resize((128, 128)))
+    assert dataset[0]["image"].shape == torch.Size((3, 128, 128))
+
+    dataset.clear_image_transforms()
+    assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
+
+
+def test_set_image_transforms_supports_lerobot_image_transforms(image_dataset):
+    dataset = image_dataset
+    dataset.add_frame({"image": np.random.rand(*DUMMY_CHW), "task": "Dummy task"})
+    dataset.save_episode()
+    dataset.finalize()
+
+    image_transforms = ImageTransforms(ImageTransformsConfig(enable=False))
+    dataset.set_image_transforms(image_transforms)
+
+    assert dataset.image_transforms is image_transforms
+    assert dataset[0]["image"].shape == torch.Size(DUMMY_CHW)
+
+
+def test_set_image_transforms_supports_loaded_dataset(tmp_path, lerobot_dataset_factory):
+    dataset = lerobot_dataset_factory(root=tmp_path / "test", use_videos=False)
+    dataset.set_image_transforms(v2.Compose([v2.Resize((224, 224)), v2.Resize((112, 112))]))
+
+    camera_key = dataset.meta.camera_keys[0]
+    assert dataset[0][camera_key].shape == torch.Size((3, 112, 112))
+
+
+def test_multilerobot_dataset_set_image_transforms_propagates(tmp_path, lerobot_dataset_factory):
+    root = tmp_path / "multi"
+    repo_ids = ["lerobot/test_multi_a", "lerobot/test_multi_b"]
+
+    for repo_id in repo_ids:
+        lerobot_dataset_factory(root=root / repo_id, repo_id=repo_id, use_videos=False)
+
+    dataset = MultiLeRobotDataset(repo_ids, root=root, download_videos=False)
+    dataset.set_image_transforms(v2.Resize((96, 96)))
+
+    camera_key = dataset.camera_keys[0]
+    assert dataset[0][camera_key].shape == torch.Size((3, 96, 96))
+    assert all(child.image_transforms is dataset.image_transforms for child in dataset._datasets)
+
+    dataset.clear_image_transforms()
+    assert dataset.image_transforms is None
+    assert all(child.image_transforms is None for child in dataset._datasets)
+
+
 def test_image_array_to_pil_image_wrong_range_float_0_255():
     image = np.random.rand(*DUMMY_HWC) * 255
     with pytest.raises(ValueError):

tests/envs/test_dispatch.py

@@ -22,6 +22,8 @@ def test_registry_all_types():
     assert len(known) >= 6
     for t in known:
         cfg = make_env_config(t)
+        if not isinstance(cfg, EnvConfig):
+            continue
         assert cfg.type == t
 
 
@@ -54,10 +56,8 @@ def test_delegation():
 
 def test_processors_delegation():
     """make_env_pre_post_processors delegates to cfg.get_env_processors()."""
-    from lerobot.configs.policies import PreTrainedConfig
-
     cfg = make_env_config("aloha")
-    pre, post = make_env_pre_post_processors(cfg, PreTrainedConfig())
+    pre, post = make_env_pre_post_processors(cfg, policy_cfg=None)
     assert len(pre.steps) == 0
 
 
@@ -124,7 +124,7 @@ def test_custom_create_envs_override():
 
 def test_custom_get_env_processors_override():
     """A custom EnvConfig subclass can override get_env_processors()."""
-    from lerobot.processor.pipeline import PolicyProcessorPipeline
+    from lerobot.processor.pipeline import DataProcessorPipeline
 
     @EnvConfig.register_subclass("_dispatch_proc_test")
     @dataclass
@@ -137,7 +137,7 @@ def test_custom_get_env_processors_override():
             return {}
 
         def get_env_processors(self):
-            return PolicyProcessorPipeline(steps=[]), PolicyProcessorPipeline(steps=[])
+            return DataProcessorPipeline(steps=[]), DataProcessorPipeline(steps=[])
 
     pre, post = _Env().get_env_processors()
-    assert isinstance(pre, PolicyProcessorPipeline)
+    assert isinstance(pre, DataProcessorPipeline)