munich-quantum-toolkit / munich-quantum-toolkit/predictor
🐛 fix RL training bug
Open
@flowerthrower is already working on this.
Since May 11, 2026.
bug
major
- Dominant language
- Python
- Stars
- 87
- Forks
- 23
- Avg merge
- 6h 23m
- Merged PRs (30d)
- 35
Description
Edge cases occurring after more than $1000$ training steps could previously cause RL training to fail. These failures remained undetected because the tests used a comparatively small step limit: https://github.com/munich-quantum-toolkit/predictor/pull/573#issuecomment-3999612466
Increase the test step limit and fix the corresponding bugs uncovered by the extended training runs. Mostly implemented by PR #573
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.