Skip to content

A 2048 AI agent trained with Q-learning and reinforcement learning algorithms to explore possible random moves in the game that can in turn yield high reward, thus enabling for exploitation of the game and yielding better gaming performance.

License

Notifications You must be signed in to change notification settings

BYTE-Club-CCNY/2048-AI

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

54 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

2048-AI

Running 2048

I have copied over the source code for a simple 2048 game. To run the game, make sure your python installation has TKinter support.

  1. Navigate to the game directory.
  2. Run python main.py.

TODO

  • Building model.py
  • Making sure agent.py runs well with model.py after building model
  • Testing and plotting data
  • Fine-tuning variables in agent for better performance
  • Implementing search algorithms so AI is able to discover best paths to achieve 2048 or higher

Feel free to add more to the README with any TODO's or documentation.

🤖

About

A 2048 AI agent trained with Q-learning and reinforcement learning algorithms to explore possible random moves in the game that can in turn yield high reward, thus enabling for exploitation of the game and yielding better gaming performance.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages