This is a very simple neural-network perceptron that attempts to solve a maze. It is fully client-side, monotonic, and requires no server; everything runs in the browser. The project is intentionally small and minimal, created to demonstrate the basic principles of AI.
Created in: 2023
Test: - Website
To get a local copy up and running follow these simple example steps.
You need to have the following things installed on your pc.
- Install any browser.
- Install
git.
Here are steps to download, build and install the following software.
- Clone the repo
git clone https://github.com/rezocrypt/MazeAI- Go to the directory
cd MazeAI - Run the project with opening index.html in any browser.
Here are main functions described.
New Maze - Generates new random maze. Reset Maze - Clears all steps done by the player and starts from the same clear maze. Step - It does exactly one step suggested by neural network. Try - Tries to solve the full maze (can take up to few seconds). Learn - It was made for learning but it doesn't work yet.
Below buttons are weights which describe by neural network (I just tried some random ones and did very simple learning).
MazeAI codebase is licensed under GNU GPLv3 license. Please refer to the LICENSE.txt file for detailed information.
Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.
If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!
- Fork the Project
- Create your Feature Branch
- Commit your Changes
- Push to the Branch
- Open a Pull Request
- Rezocrypt - Original author of the project.
- Me - Telegram - rezocrypt@gmail.com