Pepijn 0a0ebec97a fix(envs): preserve lazy-env metadata + stabilize VLABench reset ...

Two independent fixes:

1. Port of #3416: add `metadata` / `unwrapped` to `_LazyAsyncVectorEnv`
   and cache the metadata alongside obs/action spaces in the LIBERO,
   MetaWorld, and VLABench factories so async eval keeps
   `env.unwrapped.metadata['render_fps']` working.

2. VLABench `select_mahjong` kept failing the smoke eval with
   `mjWARN_BADQACC` after the 5-retry ceiling. Bump
   `_ENSURE_ENV_MAX_ATTEMPTS` to 20, reseed NumPy's global RNG
   between attempts (VLABench's upstream layout sampler is
   deterministic given current RNG state — without a reseed, retries
   replay the same diverging configuration), and raise a clearer
   `RuntimeError` on exhaustion. Also swap `select_mahjong` out of
   the CI task list in favor of `select_billiards`, which has a
   stable layout sampler.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-20 14:23:35 +02:00

..

ISSUE_TEMPLATE

chore(ci): minor improvement bug-report template & pr auto label (#2676)

2025-12-18 00:23:23 +01:00

workflows

fix(envs): preserve lazy-env metadata + stabilize VLABench reset

2026-04-20 14:23:35 +02:00

labeler.yml

chore(ci): minor improvements auto labeling (#2675)

2025-12-17 22:54:47 +01:00

PULL_REQUEST_TEMPLATE.md

chore(docs): update contributing (#3387)

2026-04-15 11:02:37 +02:00