feat(sim): VLABench benchmark integration

Add VLABench (language-conditioned manipulation with long-horizon
reasoning) as a new simulation benchmark, following the established
LIBERO/MetaWorld patterns.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pepijn
2026-04-14 11:28:17 +02:00
parent a656a982af
commit 0a3195749e
9 changed files with 795 additions and 1 deletions
+2
View File
@@ -206,6 +206,7 @@ aloha = ["lerobot[dataset]", "gym-aloha>=0.1.2,<0.2.0", "lerobot[scipy-dep]"]
pusht = ["lerobot[dataset]", "gym-pusht>=0.1.5,<0.2.0", "pymunk>=6.6.0,<7.0.0"] # TODO: Fix pymunk version in gym-pusht instead
libero = ["lerobot[dataset]", "lerobot[transformers-dep]", "hf-libero>=0.1.3,<0.2.0; sys_platform == 'linux'", "lerobot[scipy-dep]"]
metaworld = ["lerobot[dataset]", "metaworld==3.0.0", "lerobot[scipy-dep]"]
vlabench = ["lerobot[dataset]", "vlabench>=0.1.0; sys_platform == 'linux'", "mujoco==3.2.2", "dm-control==1.0.22", "lerobot[scipy-dep]"]
# All
all = [
@@ -247,6 +248,7 @@ all = [
"lerobot[phone]",
"lerobot[libero]; sys_platform == 'linux'",
"lerobot[metaworld]",
"lerobot[vlabench]; sys_platform == 'linux'",
"lerobot[sarm]",
"lerobot[peft]",
# "lerobot[unitree_g1]", TODO: Unitree requires specific installation instructions for unitree_sdk2