Update README.md

README.md

@@ -17,7 +17,7 @@ tags:
 
 - 🤠GreedRL is a fast and general framework for **Combinatorial Optimization Problems (COPs)**, based on **Deep Reinforcement Learning (DRL)**.
 
-- 🤠GreedRL achieves **1200 times faster and 3% improved performance** than [Google OR-Tools](https://developers.google.com/optimization) for large-scale (>=1000 nodes) CVRPs.
+- 🤠GreedRL achieves **1200 times faster and 3% improved performance** than [Google OR-Tools](https://developers.googleus/optimization) for large-scale (>=1000 nodes) CVRPs.
 
 ## 🏆Award
 
@@ -43,7 +43,7 @@ tags:
 We provide an open source Community Edition and an Enterprise Edition of our 🤠GreedRL for users.
 
 - **The Community Edition** is now released and available to [download](https://huggingface.co/HUANG1993/GreedRL-VRP-pretrained-v1).
-- **The Enterprise Edition** has a high-performance implementation that achives a faster computing speed, especially when solving larg-scale COPs. For more informations, please contact [us](jiangwen.wjw@alibaba-inc.com).
+- **The Enterprise Edition** has a high-performance implementation that achives a faster computing speed, especially when solving larg-scale COPs. For more informations, please contact <a href="mailto:jiangwen.wjw@alibaba-inc.com">us</a>.
 
 
 ## Architecture
@@ -573,12 +573,12 @@ We are delighted to release 🤠GreedRL Community Edition, as well as example of
 ## Installation
 First, clone the repository.
 ```aidl
-$ git clone https://huggingface.co/HUANG1993/GreedRL-VRP-pretrained-v1
+$ git clone https://huggingface.co/Cainiao-AI/GreedRL
 ```
 Then, create and activate a python environment using conda, and install required packages.
 ```aidl
 $ conda create -n python38 python==3.8
-$ conda activate python38
+$ source activate python38
 $ pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cu113
 ```
 Finally, compile and add the resulting library `greedrl` to the `PYTHONPATH`
@@ -597,21 +597,21 @@ We use generated data for the training phase, the customers and depot locations
 2. Start training
 ```python
 $ cd examples/cvrp
-$ python train.py --model_filename cvrp_5000.pt --problem_size 5000
+$ python train.py --model_filename cvrp_100.pt --problem_size 100
 ```
 
 ## CVRP Testing
 
-After training process, you'll get a trained model, like `cvrp_5000.pt`, that you can use for test.
+After training process, you'll get a trained model, like `cvrp_100.pt`, that you can use for test.
 
 ```python
 $ cd examples/cvrp
-$ python solve.py --device cuda --model_name cvrp_5000.pt --problem_size 5000
+$ python solve.py --device cpu --model_name cvrp_100.pt --problem_size 100
 ```
 
 # Support
 We look forward you to downloading it, using it, and opening discussion if you encounter any problems or have ideas on building an even better experience.
-For commercial enquiries, please contact [us](jiangwen.wjw@alibaba-inc.com).
+For commercial enquiries, please contact <a href="mailto:jiangwen.wjw@alibaba-inc.com">us</a>.
 
 # Citation
 ```
@@ -626,6 +626,3 @@ For commercial enquiries, please contact [us](jiangwen.wjw@alibaba-inc.com).
   publisher={INFORMS}
 }
 ```
-
-# About GreedRL
-- Website: https://greedrl.github.io/