feat(envs): add LIBERO-plus robustness benchmark (#3313)

* feat(envs): add LIBERO-plus robustness benchmark integration

- LiberoPlusEnv config (subclass of LiberoEnv, same gym interface)
- Docker image installing LIBERO-plus fork via PYTHONPATH
- CI workflow: 1-episode smoke eval with pepijn223/smolvla_libero_plus
- pyproject.toml: libero_plus extra

* fix(libero): use suite's perturbation-aware init_states loader

LIBERO-plus's Benchmark class exposes a `get_task_init_states(i)` method that
strips perturbation suffixes (`_table_N`, `_tb_N`, `_view_`, `_language_`,
`_light_`, `_add_`, `_level`) and loads the underlying base `.pruned_init`
file — the on-disk name for a perturbation variant doesn't exist as a file,
only the base does. lerobot's loader was bypassing that logic and trying to
read the suffix-bearing filename directly, which failed for every non-zero
task id and killed the eval before any rollout video could be written.

Delegate to the suite's method when it exists; fall back to the path-based
loader for vanilla LIBERO (which does not provide the method).

Also drop the hf-libero install + init_files copy from the LIBERO-plus
Dockerfile — the LIBERO-plus clone already ships both `bddl_files/` and
`init_files/` for all five suites, so the copy was unnecessary and the
`cp -r` into an existing dir produced a confusing nested layout.

* fix(libero): resolve LIBERO-plus perturbation init_states path ourselves

Delegating to `task_suite.get_task_init_states(i)` works for path resolution
but LIBERO-plus's method calls `torch.load(path)` without `weights_only=False`,
which fails on PyTorch 2.6+ because the pickled init_states contains numpy
objects not in the default allowlist:

    _pickle.UnpicklingError: Weights only load failed.
    WeightsUnpickler error: Unsupported global:
      GLOBAL numpy.core.multiarray._reconstruct was not an allowed global.

Mirror LIBERO-plus's suffix-stripping logic (`_table_N`, `_tb_N`, `_view_`,
`_language_`, `_light_`, `_add_`, `_level`) in our own helper so we can pass
`weights_only=False` ourselves. Vanilla LIBERO task names don't contain any
of these patterns except for `_table_` when followed by the word `center`
(e.g. `pick_up_the_black_bowl_from_table_center_...`), and the regex
requires `_table_\\d+` so semantic uses are preserved.

* fix(libero-plus): download perturbation assets from Sylvest/LIBERO-plus

LIBERO-plus's bddl_base_domain.py resolves scene XMLs with
`os.path.join(DIR_PATH, "../assets")`, so the `assets` key in config.yaml
has no effect on scene lookup — MuJoCo always opens
`<clone>/libero/libero/assets/scenes/...`. With no such directory present,
every perturbation task fails on:

    FileNotFoundError: No such file or directory:
      .../libero-plus/libero/libero/assets/scenes/tabletop_table_Cobblestone01_GLOSS_6K.xml

These textures, views, and extra objects ship only in the 6.4 GB `assets.zip`
published at `Sylvest/LIBERO-plus` (the LIBERO-plus README explicitly says
to download and unzip it into the package dir). Fetch it via `hf_hub_download`,
unzip into `${LIBERO_PLUS_ROOT}/`, install `unzip`, and point config.yaml at
the extracted dir so everything stays consistent. The download lives in its
own Docker layer so subsequent rebuilds reuse the cached assets.

Drops the lerobot/libero-assets snapshot_download — that mirror only has
vanilla LIBERO textures and is ignored for scene loading anyway.

* fix(libero-plus): flatten deep path prefix from Sylvest/LIBERO-plus assets.zip

The 6.4 GB zip ships with every entry prefixed by
`inspire/hdd/project/embodied-multimodality/public/syfei/libero_new/release/dataset/LIBERO-plus-0/assets/...`
(the author's internal filesystem layout, not the layout the LIBERO-plus
README promises), so the previous `unzip -d ${LIBERO_PLUS_ROOT}/` created
`${LIBERO_PLUS_ROOT}/inspire/.../assets/` — robosuite still opened
`${LIBERO_PLUS_ROOT}/assets/scenes/tabletop_table_Cobblestone01_GLOSS_6K.xml`
and hit the same FileNotFoundError.

Extract to a scratch dir, then `mv` the nested `assets/` subtree to the
expected location. Verified the target file exists in the zip central
directory under that exact prefix.

* refactor(libero): inline init_states resolver behind single regex

Collapse the three-style suffix stripper (split/re.sub/in) into one
compiled regex, drop the (Path, bool) tuple return, and move the
`_add_`/`_level` reshape branch into the caller so each branch loads
its own file and returns directly. Net: -11 lines, one fewer helper.

* refactor(libero-plus): rebase docker image on huggingface/lerobot-gpu

Mirror the libero/metaworld/robomme pattern: start from the nightly GPU
image (apt deps, python, uv, venv, lerobot[all] already there) and only
layer on what LIBERO-plus uniquely needs — its wand/ImageMagick build
deps, the non-extra runtime pips (robosuite==1.4.1, bddl, …), the
PYTHONPATH-shadowed fork, and the 6.4 GB assets.zip.

Drops ~50 lines of duplicated base setup (CUDA FROM, apt python, uv
install, user creation, venv init) the nightly already provides.
123 → 73 lines.

Also:
- Add libero_plus to docs/source/_toctree.yml under Benchmarks so
  doc-builder's TOC integrity check stops failing.
- Repoint the docs dataset link from pepijn223/libero_plus_lerobot to
  the canonical lerobot/libero_plus.
- Revert the stray uv.lock churn (revision/marker diff that crept in
  from an unrelated resolve — unrelated to LIBERO-plus).

* fix(libero-plus): stop touching pyproject + uv.lock

The fast-tests job was rejecting the branch because pyproject.toml had a
[libero_plus] extra whose git dep wasn't represented in uv.lock.

The Docker image no longer needs the extra — it clones LIBERO-plus
directly and PYTHONPATH-shadows hf-libero. Drop [libero_plus] from
pyproject and restore pyproject.toml + uv.lock to exactly what's on
origin/main, so `uv sync --locked --extra test` is a no-op for this PR.

Also repoint the doc/CI/env comments that still mentioned the extra at
the Docker install path.

* fix(libero-plus): strip perturbation metadata from task descriptions

LIBERO-plus builds task.language by space-joining the perturbation-variant
filename, so every non-_language_ variant inherits a trailing blob like
"view 0 0 100 0 0 initstate 0 noise 45" or "add 16". That shows up in the
dashboard video labels and no longer matches the base instruction stored
in the training dataset.

Strip those tokens in extract_task_descriptions.py with an end-anchored
regex over the {view,initstate,noise,add,tb,table,light,level}(+digits)
vocabulary. The anchor preserves mid-sentence literal uses of those words
(e.g. "from table center and place it on the plate") — only the trailing
metadata chain is removed. _language_ variants carry real BDDL-sourced
text and are left untouched.

* ci: point benchmark eval checkpoints at the lerobot/ org mirrors

pepijn223/smolvla_* → lerobot/smolvla_* across every benchmark job in
this branch (libero, metaworld, and the per-branch benchmark). The
checkpoints were mirrored into the lerobot/ org and that's the canonical
location going forward.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

* fix: integrate PR #3313 review feedback

- docs: fix paper link to arxiv, add benchmark image, add suite descriptions,
  add LIBERO-plus replacement warning, restructure eval section to match
  LIBERO doc style, fix policy I/O section, remove false try/except claim
- docker: fix shell grouping for hf-libero uninstall, replace hardcoded
  asset path with dynamic find
- ci: add Docker Hub login step, add HF_USER_TOKEN guard on eval step
- envs: add is_libero_plus param to get_task_init_states so vanilla LIBERO
  always takes the simple path

* fix(docs): use correct LIBERO-plus teaser image URL

* ci(libero-plus): drop redundant hf auth login step

The standalone login step ran `hf auth login` in a throwaway
`docker run --rm` container, so no credentials persisted. Auth is
already performed inside the eval step's container. Removing the
redundant step per PR #3313 review feedback.

* fix(envs): preserve AsyncVectorEnv metadata/unwrapped in lazy eval envs

Port of #3416 onto this branch. Without these attributes eval crashes
when calling `env.unwrapped.metadata["render_fps"]` with async vector
envs. Adds `metadata` / `unwrapped` to `_LazyAsyncVectorEnv` and
caches the metadata alongside obs/action spaces in the LIBERO and
MetaWorld factories.

* ci: gate Docker Hub login on secret availability

Fork PRs cannot access `secrets.DOCKERHUB_LEROBOT_{USERNAME,PASSWORD}`,
which made every benchmark job fail at the login step before any of
the actual build/eval work could run. Gate the login on the env-var
expansion of the username so the step is skipped (not failed) when
secrets are absent. Mirrors the existing pattern in the VLABench job.

* Update .github/workflows/benchmark_tests.yml

Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>

* Update scripts/ci/extract_task_descriptions.py

Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>

* Update .github/workflows/benchmark_tests.yml

Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>

* Update docker/Dockerfile.benchmark.libero_plus

Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>

* Update .github/workflows/benchmark_tests.yml

Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>

* fix(libero-plus): address review feedback

* ci(libero-plus): fix YAML indentation in upload-artifact steps

The `uses:` key on two upload-artifact steps was at column 0 instead
of nested under the step, causing `pre-commit run check-yaml` to fail
with "expected <block end>, but found '<block mapping start>'".


Signed-off-by: Pepijn <138571049+pkooij@users.noreply.github.com>
Co-authored-by: Khalil Meftah <khalil.meftah@huggingface.co>
This commit is contained in:
Pepijn
2026-04-20 21:07:21 +02:00
committed by GitHub
parent 282c31cfef
commit a07f22e22c
7 changed files with 466 additions and 11 deletions
+107
View File
@@ -736,3 +736,110 @@ jobs:
name: robomme-metrics
path: /tmp/robomme-artifacts/metrics.json
if-no-files-found: warn
# ── LIBERO-plus ───────────────────────────────────────────────────────────
# Isolated image: LIBERO-plus fork cloned into /home/user_lerobot on top of
# huggingface/lerobot-gpu (see docker/Dockerfile.benchmark.libero_plus).
libero-plus-integration-test:
name: LIBERO-plus — build image + 1-episode eval
runs-on:
group: aws-g6-4xlarge-plus
env:
HF_USER_TOKEN: ${{ secrets.LEROBOT_HF_USER }}
LIBERO_PLUS_SUITE: libero_spatial
LIBERO_PLUS_POLICY: lerobot/smolvla_libero_plus
LIBERO_PLUS_TASK_IDS: "[0,100,260,500,1000,1500,2000,2400]"
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
persist-credentials: false
lfs: true
- name: Set up Docker Buildx
uses: docker/setup-buildx-action@v3 # zizmor: ignore[unpinned-uses]
with:
cache-binary: false
- name: Login to Docker Hub
if: ${{ env.DOCKERHUB_USERNAME != '' }}
uses: docker/login-action@v3 # zizmor: ignore[unpinned-uses]
with:
username: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
password: ${{ secrets.DOCKERHUB_LEROBOT_PASSWORD }}
env:
DOCKERHUB_USERNAME: ${{ secrets.DOCKERHUB_LEROBOT_USERNAME }}
- name: Build LIBERO-plus benchmark image
uses: docker/build-push-action@v6 # zizmor: ignore[unpinned-uses]
with:
context: .
file: docker/Dockerfile.benchmark.libero_plus
push: false
load: true
tags: lerobot-benchmark-libero-plus:ci
cache-from: type=local,src=/tmp/.buildx-cache-libero-plus
cache-to: type=local,dest=/tmp/.buildx-cache-libero-plus,mode=max
- name: Run LIBERO-plus smoke eval (1 episode)
if: env.HF_USER_TOKEN != ''
run: |
docker run --name libero-plus-eval --gpus all \
--shm-size=4g \
-e HF_HOME=/tmp/hf \
-e HF_USER_TOKEN="${HF_USER_TOKEN}" \
-e HF_HUB_DOWNLOAD_TIMEOUT=300 \
-e LIBERO_PLUS_SUITE="${LIBERO_PLUS_SUITE}" \
-e LIBERO_PLUS_POLICY="${LIBERO_PLUS_POLICY}" \
-e LIBERO_PLUS_TASK_IDS="${LIBERO_PLUS_TASK_IDS}" \
lerobot-benchmark-libero-plus:ci \
bash -c "
hf auth login --token \"\$HF_USER_TOKEN\" --add-to-git-credential 2>/dev/null || true
lerobot-eval \
--policy.path=\"\$LIBERO_PLUS_POLICY\" \
--env.type=libero_plus \
--env.task=\"\$LIBERO_PLUS_SUITE\" \
--env.task_ids=\"\$LIBERO_PLUS_TASK_IDS\" \
--eval.batch_size=1 \
--eval.n_episodes=1 \
--eval.use_async_envs=false \
--policy.device=cuda \
'--env.camera_name_mapping={\"agentview_image\": \"camera1\", \"robot0_eye_in_hand_image\": \"camera2\"}' \
--policy.empty_cameras=1 \
--output_dir=/tmp/eval-artifacts
python scripts/ci/extract_task_descriptions.py \
--env libero_plus --task \"\$LIBERO_PLUS_SUITE\" \
--output /tmp/eval-artifacts/task_descriptions.json
"
- name: Copy LIBERO-plus artifacts from container
if: always()
run: |
mkdir -p /tmp/libero-plus-artifacts
docker cp libero-plus-eval:/tmp/eval-artifacts/. /tmp/libero-plus-artifacts/ 2>/dev/null || true
docker rm -f libero-plus-eval || true
- name: Parse LIBERO-plus eval metrics
if: always()
run: |
python3 scripts/ci/parse_eval_metrics.py \
--artifacts-dir /tmp/libero-plus-artifacts \
--env libero_plus \
--task "${LIBERO_PLUS_SUITE}" \
--policy "${LIBERO_PLUS_POLICY}"
- name: Upload LIBERO-plus rollout video
if: always()
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
with:
name: libero-plus-rollout-video
path: /tmp/libero-plus-artifacts/videos/
if-no-files-found: warn
- name: Upload LIBERO-plus eval metrics
if: always()
uses: actions/upload-artifact@v4 # zizmor: ignore[unpinned-uses]
with:
name: libero-plus-metrics
path: /tmp/libero-plus-artifacts/metrics.json
if-no-files-found: warn