Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Skill VLA eval #290

Open
wants to merge 11 commits into
base: main
Choose a base branch
from
Open

Skill VLA eval #290

wants to merge 11 commits into from

Conversation

joannetruong
Copy link
Contributor

Motivation and Context

New evaluation code for VLA policies

How Has This Been Tested

Types of changes

  • Docs change / refactoring / dependency upgrade
  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)

Checklist

  • My code follows the code style of this project.
  • My change requires a change to the documentation.
  • I have updated the documentation accordingly.
  • I have added tests to cover my changes.
  • All new and existing tests passed.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Feb 4, 2025
jimmytyyang
jimmytyyang reviewed Feb 4, 2025
View reviewed changes
Copy link
Contributor

@jimmytyyang jimmytyyang left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

look good! let's debug this when we depoly on the hardware

skill_vla/envs/base_env.py
@@ -0,0 +1,169 @@
# Copyright (c) Meta Platforms, Inc. and its affiliates.
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we recreate a new base env? what are the issues if we use the old one?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

there's a lot of stuff in the old one that might not be needed anymore, it was easier to pull out parts that I needed into this one. For an example, the old one passes the RGB images through segmentation model, whereas we now want to use the RGB as input to our policy and not use any segmentation models.

skill_vla/examples/test_skill_vla.py Outdated
policy.reset()
while not done:
action = policy.act(observations)
observations, _, done, _ = env.step(base_action=action)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

good point! I guess what you do here is to create a simple while loop RL env, so that we do not need to go through the complex existing env stuff

@joannetruong joannetruong changed the title initial commit to add skill vla eval Skill VLA eval Feb 6, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jimmytyyang jimmytyyang jimmytyyang left review comments

At least 1 approving review is required to merge this pull request.

Assignees
No one assigned
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@joannetruong @jimmytyyang @facebook-github-bot @tusharsangam