Update README.md

README.md

@@ -1,11 +1,24 @@
+# 🏆 VRP Shanghai Transformer
+
+> Transformer-based Reinforcement Learning Model for Vehicle Routing Problem (VRP) with Time Windows,
+> trained and tested on the Shanghai delivery dataset.
+
 ---
-title: Vrp Shanghai Transformer
-emoji: 🏆
-colorFrom: purple
-colorTo: yellow
-sdk: docker
-pinned: false
-license: mit
+
+## 🚀 Project Description
+
+This project implements a deep reinforcement learning (DRL) agent based on the 
+**Transformer architecture** to solve the **Vehicle Routing Problem with Time Windows (VRPTW)**. 
+The model is adapted from the paper [Attention, Learn to Solve Routing Problems!](https://arxiv.org/abs/1803.08475) 
+and is tested on real-world delivery data from Shanghai.
+
+It leverages a combination of:
+- Transformer Encoder-Decoder architecture
+- Pointer Networks
+- Beam Search Decoding
+- OR-Tools for benchmarking
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+## 🗂️ Project Structure
+