Skip to content

Fix tags in reward design #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix tags in reward design #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@ We design an RL training pipeline to train a base model for generating [Triton K

We design the reward function with two components:

1. ✅ Format Checking: Validate correct usage of `<thinking>` and `<answer>` tags.
1. ✅ Format Checking: Validate correct usage of `<think>` and `<answer>` tags.
2. 🔍 Similarity Score: Measure string similarity between generated and ground-truth Triton kernels using Python’s `difflib.SequenceMatcher`. This idea is inspired by [`SWE-RL`](https://arxiv.org/abs/2502.18449).

### 🧪 Evaluation
Expand Down