Skip to content

P-mir/Q-learning-Blackjack

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Reinforcement Learning: Learning How to count cards at Blackjack

Introduction

In this project I use RL to make an agent learn the optimal blackjack strategy to play. The optimal action to play is given by the Bellman equation

In a second time it is demonstrated that the agent can learn to leverage a simple card counting strategy to improve its games and beat the casino.

Instructions

Run the script Environment.R to launch the game.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published