Skip to content

Implementation of some Reinforcement Learning algorithms for the Tic Tac Toe game

Notifications You must be signed in to change notification settings

nathanael-fijalkow/MonteCarloTreeSearch

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

13 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

MonteCarloTreeSearch

This repository contains a clean, simple, and generic implementation of Monte Carlo Tree Search.

For testing purposes it is applied to the game of Tic Tac Toe through a simple API which is (heavily) inspired by Jeff Bradberry's own code (https://github.com/jbradberry).

Contents

  • tictactoe.py: the game of Tic Tac Toe
  • optimal.py: an optimal player (computing the value through min-max algorithm)
  • MCTS.py: the main file, generic implementation of MCTS. Can use epsilon-greedy or UCB as simulation strategy and average, step-size, or temporal difference for backpropagation
  • tests.py: a series of tests

About

Implementation of some Reinforcement Learning algorithms for the Tic Tac Toe game

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages