README.md

中文版本的 README

Q-Learning-Demo

A project show how Q-learning works from scratch

Blog

基于 OpenAI Gym 的 Q-Learning 算法演示

Getting Started

Download or git clone this repository.

Proof of concept

Online demo

A Jupyter notebook is provided to demo online. Link is here.

Prerequisites

Python 3.5+

Check you python version with this

python --version

Installing

Git clone the code

git clone https://github.com/howl-anderson/q_learning_demo.git

then

cd q_learning_demo

Running the training

You can train your model or skip this to used pre-trained model

python -m q_learning_demo.train

Running the pre-trained model

Use built-in pre-trained model to test model

python -m q_learning_demo.load

Built With

• OpenAI Gym - The reinforcement framework used

Contributing

Please read CONTRIBUTING.md for details on our code of conduct, and the process for submitting pull requests to us.

Versioning

We use SemVer for versioning. For the versions available, see the tags on this repository.

Authors

• Xiaoquan Kong - Initial work - howl-anderson

See also the list of contributors who participated in this project.

License

This project is licensed under the MIT License - see the LICENSE.md file for details

Acknowledgments

• Billie Thompson - For README.md & CONTRIBUTING.md template