fix(isaaclab): normalize observations before first policy act#8
Open
Abhishek21g wants to merge 1 commit into
Open
fix(isaaclab): normalize observations before first policy act#8Abhishek21g wants to merge 1 commit into
Abhishek21g wants to merge 1 commit into
Conversation
The initial observation from get_observations() was passed to act() without empirical normalization, while all subsequent rollout steps normalize obs after env.step(). Align with rsl_rl behavior and fix amazon-far#6.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fixes #6 — the first observation from
get_observations()was passed toact()without empirical normalization, while all subsequent rollout steps normalize obs afterenv.step().Adds normalization before the training loop starts, matching rsl_rl behavior.
Changes
on_policy_runner.py: normalizeobsandprivileged_obsbefore the firstact()callTest plan
empirical_normalization=False, normalizers areIdentity(no-op)Note
No GPU available locally for author verification; fix is a clear consistency bug from code review.