[rllib] Prevent double calling connectors for MultiAgentEnvRunner's completed episodes when sampling a fixed number of episodes
#58931
+88
−9
Conversation
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
added 2 commits
November 23, 2025 13:38
… final episode when sampling a fixed number of episodes Signed-off-by: Mark Towers <[email protected]>
Signed-off-by: Mark Towers <[email protected]>
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request effectively resolves an issue where a connector callback was being invoked twice for the final episode in a batch. The fix is well-implemented by conditionally skipping the on_episode_created callback for the transient, newly created episode that replaces the final completed one. The added test case, which uses a custom EpisodeTracker connector, is a great way to verify the fix and ensure the callback is only triggered once per completed episode. I have one minor suggestion to improve the test code's style.
Signed-off-by: Mark Towers <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Description
The
MultiAgentEnvRunnerwould previously call the callback twice for the final episode of a batch (when sampling a fixed number of episodes). This PR fixes this problem ensuring that the callback only happens once for finished episodeRelated issues
Closes #55452