[RLlib] Add IS APPO metrics to torch learner#63675
Merged
ArturNiederfahrenhorst merged 4 commits intoJun 3, 2026
Merged
Conversation
Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com>
ArturNiederfahrenhorst
added
rllib
![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 ports the mean_IS and var_IS diagnostics for the importance sampling (IS) ratio from the old TensorFlow policy to the PyTorch APPO learner. The reviewer suggested using torch.square instead of torch.pow(..., 2.0) for better performance and idiomatic PyTorch code.
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> Signed-off-by: Artur Niederfahrenhorst <attaismyname@googlemail.com>
rueian
pushed a commit
to rueian/ray
that referenced
this pull request
Jun 4, 2026
## Description The old stack (for example the loss defined in our APPO TF policy) had importance sampling metrics to track off-policyness. This PR introduces the same two metrics to the new stack. --------- Signed-off-by: Artur Niederfahrenhorst <artur@anyscale.com> Signed-off-by: Artur Niederfahrenhorst <attaismyname@googlemail.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
The old stack (for example the loss defined in our APPO TF policy) had importance sampling metrics to track off-policyness.
This PR introduces the same two metrics to the new stack.