modelscope / modelscope/ms-swift
get_reward方法的归一化逻辑是不是有问题？
Open
Nobody has claimed this yet.
stale
- Dominant language
- Python
- Stars
- 15.7k
- Forks
- 1.7k
- Avg merge
- 1d 16h
- Merged PRs (30d)
- 136
Description
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.
Research direction
Start by locating the get_reward entry point and inspect how threshold masking and min_val/max_val selection interact. Reproduce the reported case with threshold=-1, one reward of -10000, and other rewards between -1 and 1; done means normalization uses the intended unmasked reward values and the behavior is covered by an appropriate test.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100