Skip to content

A "from scratch" adversarial AI agent (minimax w/ alpha-beta pruning) applied to the zero-sum game of Mancala. One player is human, the other is the agent.

Notifications You must be signed in to change notification settings

dustinfast/mancala_agent

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Mancala Agent

A Human vs Computer Manacala game - Built as demonstration of an adversarial AI applied to the zero-sum game of Mancala. Uses a minimax algorithm with alpha/beta pruning to competently compete against the user.

alt text

Usage

Complile with g++ mancala.cpp (or equivelant). Run with ./mancala [ MAX_SEARCH_DEPTH ]

MAX_SEARCH_DEPTH

The minimax algorithm parses it's decision space as a tree. MAX_SEARCH_DEPTH defines the maximum depth to which the algorithm may traverse before it must choose its move. A higher max depth will give a "smarter" agent, but at a geometrically increasing cost to performance.

About

A "from scratch" adversarial AI agent (minimax w/ alpha-beta pruning) applied to the zero-sum game of Mancala. One player is human, the other is the agent.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages