policy

vla-evaluation-harness

allenai · PyTorch

or hover any field below to flag it

Overview

Name

vla-evaluation-harness

Author

allenai

Framework

PyTorch

License

Apache-2.0

Skill type

other

Evidence level

community

Task description

One framework to evaluate any VLA model on any robot simulation benchmark.

Spaces

Action space

other · 0-dim · 0Hz

Observation space

type: other

Links

HuggingFace repo

null

Paper (arXiv)

null

Compatible robots

19

irmvlab-unihandnot in seed nvlabs-handover-simnot in seed irvlab-poseidennot in seed denghaoyuan123-awesome-rl-vlanot in seed guoheyu-omnivlanot in seed ananasburn-smolvla-manipulationnot in seed zhenyangliu-activevla-injecting-active-perception-into-vlanot in seed allenai-vla-evaluation-harnessnot in seed vlad-brasoveanu-stm32-robotic-arm-6dofnot in seed openhelix-team-openhelixnot in seed rk-edge-simscaleainot in seed sonjuonr-visual-fusion-grunot in seed wwzzz-ilstudionot in seed abdelrahmanfarhan-vla-panda-mujoconot in seed nvlabs-protomotionsnot in seed ivlabs-autonomous-delivery-robotnot in seed zainali24-physical-ai-humanoid-roboticsnot in seed shiv207-vla-simulated-testsnot in seed internrobotics-vlacnot in seed

Compatible environments

0

No environments list vla-evaluation-harness yet.

Datasets that reference this policy

0

No datasets reference vla-evaluation-harness yet.