Update README.md

README.md

@@ -13,13 +13,11 @@ tags:
 
 # 🤠GreedRL
 
-## Introduction
+## Overview
 
-  ***Combinatorial Optimization Problems (COPs)*** has long been an active field of research. Generally speaking, there exists two main approaches for solving COPs, each of them having pros and cons. On one hand, the *exact algorithms* can find the optimal solution, but they may be prohibitive for solving large instances because of the exponential increase of the execution time.
-  On the other hand, *heuristic algorithms* can compute solutions efficiently, but are not able to guarantee the optimality of solutions.
+- 🤠GreedRL is a fast and general framework for **Combinatorial Optimization Problems (COPs)**, based on **Deep Reinforcement Learning (DRL)**.
 
-  In the realistic business scenarios, COPs are usually large-scale (>=1000 nodes), which have very strict requirements for the execution time and performance of solutions. To better solve these problems, we
-  propose a generic and complete solver, named **🤠GreedRL**, based on **Deep Reinforcement Learning (DRL)**, which achieves improved speed and performance of solutions than *heuristic algorithms* .
+- 🤠GreedRL achieves **1200 times faster and 3% improved performance** than [Google OR-Tools](https://developers.google.com/optimization) for large-scale (>=1000 nodes) CVRPs.
 
 ## 🏆Award
 
@@ -30,15 +28,17 @@ tags:
 
 * **GENERAL**
   
-  🤠GreedRL makes **a high level of abstraction for COPs**, which can solve various types of problems, such as Vehicle Routing Problems(VRPs), Batching, Scheduling and Online Assignment problems. At the same time, for the VRPs, it also supports variants of VRPs with different constraints, such as Time-Window, Pickup-Delivery, Split-Delivery, Multi-Vehicles, etc.
+  🤠GreedRL makes **a high level of abstraction for COPs**, which can solve various types of problems, such as TSP, CVRP, VRPTW, PDPTW, SDVRP, DPDP, Order Batching, etc.
 
 * **HIGH-PERFORMANCE**
 
-  🤠GreedRL have improved the DRL environment (Env) simulation speed by **CUDA and C++ implementations**. At the same time, we have also implemented some **Operators** to replace the native operators of PyTorch, like *Masked Matrix Multiplication* and *Masked Additive Attention*, to achive the ultimate computing performance.
+  🤠GreedRL have improved the DRL environment (Env) simulation speed by **CUDA and C++ implementations**.
   
 * **USER-FRIENDLY**
 
-  🤠GreedRL have **warped commonly used modules**, such as Neural Network (NN) components, RL training algorithms and COPs constraints implementations, which makes it easy to use.
+  🤠GreedRL framework provides **user-friendly ability for COPs modeling**, where users only need to declare constraints, objectives and variables of COPs.
+
+  For more detailed examples, please refer to [COPs Modeling examples].
 
 ## Architecture
   ![](./images/GREEDRL-Framwork_en.png)