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.

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

[BugFix] Vmap randomness for value estimator #1942

Merged
merged 1 commit into from
Feb 21, 2024

Conversation

BY571
Copy link
Contributor

@BY571 BY571 commented Feb 21, 2024

Description

Solving the issue in #1935

Motivation and Context

Why is this change required? What problem does it solve?
If it fixes an open issue, please link to the issue here.
You can use the syntax close #15213 if this solves the issue #15213

  • I have raised an issue to propose this change (required for new features and bug fixes)

Types of changes

What types of changes does your code introduce? Remove all that do not apply:

  • Bug fix (non-breaking change which fixes an issue)
  • New feature (non-breaking change which adds core functionality)
  • Breaking change (fix or feature that would cause existing functionality to change)
  • Documentation (update in the documentation)
  • Example (update in the folder of examples)

Checklist

Go over all the following points, and put an x in all the boxes that apply.
If you are unsure about any of these, don't hesitate to ask. We are here to help!

  • I have read the CONTRIBUTION guide (required)
  • My change requires a change to the documentation.
  • I have updated the tests accordingly (required for a bug fix or a new feature).
  • I have updated the documentation accordingly.

Copy link

pytorch-bot bot commented Feb 21, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/1942

Note: Links to docs will display an error until the docs builds have been completed.

❌ 4 New Failures, 1 Unrelated Failure

As of commit e063699 with merge base 13bef42 (image):

NEW FAILURES - The following jobs have failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@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 21, 2024
@BY571
Copy link
Contributor Author

BY571 commented Feb 21, 2024

@vmoens What do you think of this?

It would allow us to do:

# sets default randomness to different when dropout is detected 
advantage_module = GAE(
        gamma=0.99, lmbda=0.95, value_network=value_module, average_gae=True
    )

# But can set vmap randomness manually to 'same'/'different': 
advantage_module.set_vmap_randomness("same")

@vmoens vmoens added bug Something isn't working Suitable for minor Suitable to be integrated in minor release (no new feature) labels Feb 21, 2024
@vmoens vmoens linked an issue Feb 21, 2024 that may be closed by this pull request
3 tasks
Copy link
Contributor

@vmoens vmoens left a comment

Choose a reason for hiding this comment

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

LGTM! Thanks for taking care of this

@BY571 BY571 marked this pull request as ready for review February 21, 2024 20:27
@vmoens vmoens merged commit 4080cf3 into pytorch:main Feb 21, 2024
63 of 68 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. Suitable for minor Suitable to be integrated in minor release (no new feature)
Projects
None yet
Development

Successfully merging this pull request may close these issues.

[BUG] Using Dropout in a ValueOperator results in RuntimeError
3 participants