chore(deps): bump unilab-rl to 1.4.3 - #1662
Merged
Merged
Conversation
Picks up the off-policy collector shutdown fix: normal training completion no longer crashes the lock-step collector with "Learner stopped before inference tick". uv.lock / uv.rocm.lock regenerated with the pinned uv 0.12.5, which also normalizes dependency markers lockfile-wide.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bumps the
unilab-rlpin from 1.4.2 to 1.4.3 (uni_rlextra + dev group, CUDA and ROCm manifests).unilab-rl 1.4.3 fixes the spurious collector crash after normal off-policy training completion:
RuntimeError: Learner stopped before inference tick N(e.g. afteruv run --extra mjwarp train --algo sac --task g1_walk_flat --sim mjwarp algo.max_iterations=10, the run completed and savedmodel_10.pt, then the collector exited with code 1). Root cause and fix: unilabsim/unilab_rl#52 — the runner now requests collector stop before publishing theSTOPPEDlearner phase.Release: https://github.com/unilabsim/unilab_rl/releases/tag/v1.4.3 (PyPI
unilab-rl==1.4.3).Changes
pyproject.toml,pyproject.rocm.toml:unilab-rl==1.4.2→==1.4.3(extra + dev group)uv.lock,uv.rocm.lock: regenerated with the pinned uv 0.12.5; includes lockfile-wide marker normalization by this uv version (cosmetic, no version changes other than unilab-rl)Validation
uv sync --extra mujoco --extra motrix --extra uni_rlresolves and installsunilab-rl==1.4.3from PyPIuv run --extra mjwarp train --algo sac --task g1_walk_flat --sim mjwarp algo.max_iterations=10completes cleanly — 10/10 iterations,model_10.ptsaved, ONNX export verified, no collector error (previously reproducible crash)