Skip to content

The absolute most basic example of AlphaZero and Monte Carlo Tree Search I could come up with

License

Notifications You must be signed in to change notification settings

mjosephan2/AlphaZeroSimple

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

AlphaZeroSimple

Blog: http://joshvarty.github.io/AlphaZero/

Video: https://www.youtube.com/watch?v=62nq4Zsn8vc

The absolute most basic example of AlphaZero and Monte Carlo Tree Search I could come up with. This implementation plays a game called Connect2:

In Connect2 players alternate between playing pieces on a tiny 1x4 board with the goal of placing two of their pieces side-by-side. It’s comically easy to win as the first player, but Connect2 still has the interesting property that either player technically has the chance to win, lose or draw.

Dependencies

  • PyTorch
  • kaggle_environments (Optional: Allows you to play against the model)

Based On:

About

The absolute most basic example of AlphaZero and Monte Carlo Tree Search I could come up with

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%