Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Comments

[Feature] Add option for auto-resetting envs in GAE#2851

Merged
vmoens merged 1 commit intopytorch:mainfrom
lin-erica:elin/autoreset-gae
Apr 14, 2025
Merged

[Feature] Add option for auto-resetting envs in GAE#2851
vmoens merged 1 commit intopytorch:mainfrom
lin-erica:elin/autoreset-gae

Conversation

@lin-erica
Copy link
Contributor

Description

Previously, when calculating the GAE, torchrl assumes that there is a valid s_(t+1) return from the environment. However, for auto-resetting environments, that is not true at the end of the episode, as it just jumps to the first state of the next episode. This PR adds a feature to the GAE class, allowing users to specify if it's an auto-resetting env, in which case it will use the s_t as an approximation for bootstrapping.

Motivation and Context

Without this change, we were getting much slower convergence rates during training for IsaacLab (an autoresetting env).

  • 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.

@pytorch-bot
Copy link

pytorch-bot bot commented Mar 14, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/2851

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

❌ 11 New Failures, 1 Cancelled Job, 1 Unrelated Failure

As of commit cae5b6f with merge base 9cd95d5 (image):

NEW FAILURES - The following jobs have failed:

CANCELLED JOB - The following job was cancelled. Please retry:

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 Mar 14, 2025
@lin-erica
Copy link
Contributor Author

@vmoens Perhaps I missed it, but I didn't see any tests that were testing the GAE class. If there is, I'm happy to add a relevant test as well.

@lin-erica lin-erica changed the title initial commit [Feature] Add GAE for auto-resetting envs Mar 14, 2025
@lin-erica lin-erica changed the title [Feature] Add GAE for auto-resetting envs [Feature] Add option for auto-resetting envs in GAE Mar 14, 2025
Copy link
Collaborator

@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! Sorry for the delay in reviewing this!

To answer your question: Not sure what unit test we want for this feature, so I'm willing to consider merging it as is.

We do test the GAE in test_costs.py I believe... I you have an idea of what to test we can add it

@vmoens vmoens added the enhancement New feature or request label Apr 14, 2025
@vmoens vmoens merged commit f5f3ae4 into pytorch:main Apr 14, 2025
59 of 72 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants