[Feature] Add Safety-Gymnasium environment wrapper#3689
Merged
vmoens merged 4 commits intopytorch:mainfrom Apr 29, 2026
Merged
Conversation
Adds SafetyGymnasiumWrapper and SafetyGymnasiumEnv for constrained-RL benchmarks. The underlying step API returns a 6-tuple with a parallel cost signal; the wrapper folds cost into the gymnasium info dict so the existing GymWrapper machinery is reused, then registers an info-dict reader that exposes cost as a top-level tensordict key alongside reward.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/rl/3689
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ⏳ No Failures, 16 PendingAs of commit 40ab5e5 with merge base 471e813 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
github-actions
Bot
added
Feature
vmoens
reviewed
Apr 28, 2026
github-actions
Bot
added
Documentation
Contributor
|
Looks like the original issue for call for contributions got closed because the PR comment mentioned that this PR fixes the issue |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Adds SafetyGymnasiumWrapper and SafetyGymnasiumEnv for constrained-RL benchmarks. The underlying step API returns a 6-tuple with a parallel cost signal; the wrapper folds cost into the gymnasium info dict so the existing GymWrapper machinery is reused, then registers an info-dict reader that exposes cost as a top-level tensordict key alongside reward.
##Motivation
Fixes #509
Adds SafetyGymnasiumWrapper and SafetyGymnasiumEnv for constrained-RL
benchmarks. The underlying step API returns a 6-tuple with a parallel
cost signal; the wrapper folds cost into the gymnasium info dict so the
existing GymWrapper machinery is reused, then registers an info-dict
reader that exposes "cost" as a top-level tensordict key alongside
"reward".