A personal project to showcase my way of working.
This project consists of training an AI Agent to play Snake (coded in PyGame).
The DRL methods used to train the agent is Deep Q-Learning.
Use the commands below to create a virtual environment using the pip package manager.
pip install virtualenv
virtualenv ai-snake
ai-snake\scripts\activate #backslash is important (not /)
pip install -r requirements.txtpython3 trainer.pyTo deactivate the current environment, use the following command:
deactivateTODO:
- Demo from checkpoint
- GUI Web app demo
- Add double DQN trainer
Pull requests are welcome. For major changes, please open an issue first to discuss what you would like to change.
Please make sure to update tests as appropriate.
To Patrick Loebar for the starter code. My intention for this project is to refactor the starter code and to extend the project with a GUI and more sophisticated DRL methods. As you can see by my activity, this is an ongoing project (as of June 2023).