https://github.com/avinashbot/gamesearch

Monte Carlo Tree Search for {Tic Tac Toe, Connect 4, Mancala} implemented in Haskell.
https://github.com/avinashbot/gamesearch

ai connect-four haskell kalah mancala mancala-game monte-carlo-tree-search tic-tac-toe

Last synced: 3 months ago
JSON representation

Monte Carlo Tree Search for {Tic Tac Toe, Connect 4, Mancala} implemented in Haskell.

• Host: GitHub
• URL: https://github.com/avinashbot/gamesearch
• Owner: avinashbot
• License: bsd-3-clause
• Created: 2017-05-31T20:24:34.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2017-06-17T20:37:40.000Z (almost 8 years ago)
• Last Synced: 2025-01-03T08:47:30.253Z (5 months ago)
• Topics: ai, connect-four, haskell, kalah, mancala, mancala-game, monte-carlo-tree-search, tic-tac-toe
• Language: Haskell
• Homepage:
• Size: 87.9 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
**(gamesearch is)**

- a mostly general-purpose implementation of **multiplayer [Monte Carlo Tree Search](https://en.wikipedia.org/wiki/Monte_Carlo_tree_search)**.

- written in **purely functional Haskell**.

- contained in **~100 SLOC** ([Core.hs](https://github.com/avinashbot/gamesearch/blob/master/src/Game/GameSearch/Core.hs)).

- made by [**@avinashbot**](https://github.com/avinashbot).

**(gamesearch has)**

- demos for **Tic Tac Toe**, **Connect Four**, and **Mancala (Kalah)**.

- support for **weighted (heavy) playouts**.

**(gamesearch doesn't yet)**

- support adjusting exploration vs. exploitation.