anakin87/qwen-scheduler-grpo

Train a Language Model with GRPO to create a schedule from a list of events and priorities

38
/ 100
Emerging

This project explores teaching a language model to create schedules. You provide a list of events with their start/end times and specify which events have higher priority. The model then generates an optimized schedule that prioritizes important tasks and aims to maximize the total duration of selected events. This is for researchers and developers experimenting with reinforcement learning for large language models.

264 stars. No commits in the last 6 months.

Use this if you are a researcher or developer interested in novel approaches to training LLMs with reinforcement learning without explicit examples.

Not ideal if you need a production-ready scheduling tool that reliably avoids all event overlaps, as the current model still struggles with this specific constraint.

reinforcement-learning language-model-training experimental-ai schedule-optimization llm-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

264

Forks

16

Language

Jupyter Notebook

License

Apache-2.0

Category

llm-fine-tuning

Last pushed

Apr 29, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/anakin87/qwen-scheduler-grpo"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.