|
|
--- |
|
|
license: unknown |
|
|
language: |
|
|
- en |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-1.5B-Instruct |
|
|
pipeline_tag: text-generation |
|
|
tags: |
|
|
- agent |
|
|
--- |
|
|
This repository has weights of an **LLM agent** that learns to solve the logic puzzle **Masyu** (Necklace) using **Reinforcement Learning** with the **GRPO algorithm**. |
|
|
|
|
|
 |
|
|
|
|
|
These are my results of training Qwen/Qwen2-1.5B-Instruct. Due to constraints on available computational resources, a significant improvement in performance was primarily achieved for the first four difficulty levels. More extensive training—with more steps, a larger base model, or higher num_generations—would likely be required to achieve improvements on more complex puzzles. |
|
|
|
