Add reinforcement-learning pipeline tag to model card

This PR enhances the model card by adding the `pipeline_tag: reinforcement-learning` to the metadata. This will improve the model's discoverability on the Hugging Face Hub, as the model implements an imitation learning-based branching policy for SAT solvers, a method related to reinforcement learning.

README.md

@@ -1,6 +1,8 @@
 ---
 license: apache-2.0
+pipeline_tag: reinforcement-learning
 ---
+
 <p align="center">
   <h1 align="center"><em>ImitSAT</em>: Boolean Satisfiability via Imitation Learning</h1>
   <!-- <br /> -->
@@ -57,4 +59,4 @@ tokenizer/
       primaryClass={cs.AI},
       url={https://arxiv.org/abs/2509.25411}, 
 }
-```
+```