Repository navigation
Add transactional grouped rollout semantics - #93
Merged
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
n > 1Parquet prompt samples through new direct-GKD and sampled-k1 grouped profiles without changing the measuredn = 1profilesThe grouped samples are independent current-policy trajectories. This does not add a group baseline, GRPO, a new reward, or a new benchmark. The two grouped profiles are conformance-only.
Validation
git diff --checkruff check .ruff format --check .mypy src/miniverlpytest -q -m "not gpu and not network" --cov=miniverl: 2423 passed, 9 platform skips, 83% coveragepytest -q -m gpu: 10 passedpytest -q -m network: 16 passedmkdocs build --stricttwine checkLocal development build hashes:
c32542c884a9f582b26e0229c62b5da3a72867148311799b29cfc61a00c2b2f9a3bf8b3625c868f4d0ff44ec61768e76816741ac204def3ce3db54a8fd28f4fdFrozen evidence remains byte-identical:
53fc1d4d5b7adee09618d77ad62d4086ba56b78569832d6fc7c3bcd5c2695bbcb25daee7ee726b7a7be18d7dbe26590fb61325bf212cfd9e7110b69f5fa8889c