By: Jonathan Quenzer. To have a computer learn how to play Blackjack through reinforcement learning Computer starts off with no memory. After each hand.

Slides:



Advertisements
Similar presentations
Card Counting Driller By Oscar Chen For CS491A. Practice your Card Counting Skills Application to allow Blackjack Enthusiasts to sharpen their skills.
Advertisements

Math and Card Games By: Candace DiBiano.
Driving Rules: Signs and Symbols 1.Identify sign or symbol on the road 2.Explain what it means.
Cribbage A fun game of counting. What is Cribbage Cribbage is a card game for two players. Described by some as 'a game of low, animal cunning', it demands.
© Glenn Rowe AC Lab 2 A simple card game (twenty- one)
Probability, matrices and game theory The mathematics of Blackjack (21)
It’s All in the Cards Adding and Subtracting Integers
Lecture 11. R function Function is a wrapper that allows us to write code in modules Back to Handout Homework: Create a function for drunken sailor –
Name: Trương Hoài Anh Facebook: Quasar Hoaianh
Assignment 2 Observations
EGR 141 Computer Problem Solving in Engineering and Computer Science
Lecture 10. Simplified roulette European roulette has numbers 0,1,…36. xD0s
Dealer Comm Hand Player makes Ante bet and optional Bonus bet. Five cards are dealt to each player from the shuffler. Five cards are dealt from the shuffler.
Card Counting What is it, how does it work, and can I use it to pay for college? (and if it does work, do I even have to go to college?) Jeff O’Connell.
BLACKJACK SHARKS: Aabida Mayet, Omar Bacerra, Eser Kaptan March 15, 2010.
Dice, Cards and Darts Probabilities in Games Finding the Right Representation.
An application of the Probability Theory
Rene Plowden Joseph Libby. Improving the profit margin by optimizing the win ratio through the use of various strategies and algorithmic computations.
Computer Science 313 – Advanced Programming Topics.
MATH CLASH Integer Addition Game 1. Player Rules Players must be paired with another person Cards must be evenly divided at the start of the round Players.
Analysis and Strategy 1) They can’t all be homers.
Intro to Probability & Games
Test Abstractions Intent Nat. Lang. Spec. HW Behavioral Tests can be described at different abstraction levels Tests can be defined top-down or bottom-up.
Rapid Recall Activities. Retention of facts is key with the New Curriculum Rolling Dice: Rolling a 10-sided dice and making number bonds to 10 Adding.
Black Jack Dr. Bernard Chen University of Central Arkansas Spring 2012.
Blackjack: A Beatable Game
Blackjack: Myths vs. Reality Group K Andrew KerrAndrew Phillips Sven SkoogWoj Wrona.
Blackjack: An Analysis of Probability By: John Theobald.
April 2009 BEATING BLACKJACK CARD COUNTING FEASIBILITY ANALYSIS THROUGH SIMULATION.
Poker UML and ADT design plan.
Casinos There’s a reason they are big and extravagant!
1 Introduction to Discrete Probability Rosen, Section 6.1 Based on slides by Aaron Bloomfield and …
Combinations Problems Problem 1: Sometimes we can use several counting techniques in the same problem, such as combinations and the addition principle.
Learning to Play Blackjack Thomas Boyett Presentation for CAP 4630 Teacher: Dr. Eggen.
Paigow Training Hai J Shen International Association of Certified Surveillance Professionals.
Inner and Anonymous Classes Though you are captive in the OO paradigm, you can use inner classes and anonymous classes to get around this constraint and.
Objective Probabilities
Learning BlackJack with ANN (Aritificial Neural Network) Ip Kei Sam ID:
Blackjack: A Beatable Game Amber Guo Adapted from: David Parker Advisor: Dr. Wyels California Lutheran University ‘05.
Think About Ten 3-2 Carlos Suzy x
Dice Games for Math. Multiplication War Skill: Multiplication facts to 36 Players: 2 to 4 players Supplies: 2 dice and counters (such as M&Ms, Cheerios,
Blackjack Betting and Playing Strategies: A Statistical Comparison By Jared Luffman MSIM /3/2007.
1 M14 Expected Value, Discrete  Department of ISM, University of Alabama, ’95,2002 Lesson Objectives  Understand the meaning of “expected value.” (Know.
The Elements. The Cards 地 : Earth 水 : Water 火 : Fire 風 : Air 空 : Void/Spirit.
Do Now 9/28/10 Take out your HW from last night. Take out your HW from last night. Textbook page 31-32, #3-11, all Textbook page 31-32, #3-11,
Do Now 10/3/11 Take out your HW from Wednesday. Take out your HW from Wednesday. Textbook page 54, #1-4 all, all, all, 56 Textbook page 54,
THE NATURE OF PROBABILITY Copyright © Cengage Learning. All rights reserved. 13.
1 DIG Lecture 2 (Game) The Acey-Deucey Game Michael Moshell University of Central Florida Media Software Design.
Gambling Because why not?. Blackjack and card counting Card counting is a casino card game strategy used primarily in the blackjack family of casino games.
WOULD YOU PLAY THIS GAME? Roll a dice, and win $1000 dollars if you roll a 6.
Do Now 9/17/09  Take out HW from last night. Textbook page 32 #14-40 even, #48-58 even Textbook page 32 #14-40 even, #48-58 even  Copy HW in your planner.
In the Kitchen Use recipes for fractions How much is 1,1/2, ¼ cup? How many ¼ are in a cup? Let your student measure the ingredients. Double the recipe/half.
GamblingGambling What are the odds? Jessica Judd.
Random Numbers Random numbers are extremely useful: especially for games, and also for calculating experimental probabilities. Formula for generating random.
Week 8 : User-Defined Objects (Simple Blackjack Game)
The Pentium Goes to Vegas Training a Neural Network to Play BlackJack Paul Ruvolo and Christine Spritke.
Gambling and probability 1. Odds and football.  Predict the Premier League results for this weekend.  Can you estimate the probability of a win/draw/loss.
Math in the gamble. Poker is Math Poker is a game that requires the ability to read situations and your opponents to gain an advantage in every hand you.
Discrete Optimization MA2827 Fondements de l’optimisation discrète Dynamic programming (Part 2) Material based on.
Lecture 13.
Lecture 11.
Lecture 10.
Probability of casino games
Lecture 12.
ROULETTE Yasmina, Phoebe, and Roshen.
Blackjack: Counting Hands and Counting Cards
Agenda Warmup Lesson 1.9 (random #s, Boolean variables, etc)
Do Now 9/28/11 Take out HW from last night. Copy HW in your planner.
BY: Cesar, Jennifer, Adrianne & Allen
Agenda Warmup Lesson 1.9 (random #s, Boolean variables, etc)
Presentation transcript:

By: Jonathan Quenzer

To have a computer learn how to play Blackjack through reinforcement learning Computer starts off with no memory. After each hand is played, the computer learns more. Goal is to have computer make the best possible decision of how much to bet and when to hit/stay Splitting hands and doubling down will not be included. This decreases the odds of winning.

The dealer has a 5-8% advantage depending on the specific rules without using card counting The player through correct strategy and using card counting can obtain at most a 2% advantage on the dealer

I wrote a Matlab program to simulate Black Jack. Feature vectors were generated by running the program and analyzing each hand played. All of the features were scaled to have a mean of ½, minimum of 0, and maximum of 1.

Hand History Ace The number of cards remaining in the deck for each value of card 2 … 10 PTPlayer Total Without Aces PANumber of Aces in Player's Hand DSCThe Dealers Showing Card Hit/Stay+1 = Hit, -1 = Stay Win1.5 = Black Jack, 1 = Win, 0 = Lose Lose1 = Lose, 0 = Win Push1 = Push, 0 = Win Feature Set Hit/Stay Ace The number of cards remaining in the deck for each value of card 2 … 10 CC Calculated Card Count: Hi-Opt II used PTPlayer Total Without Aces PANumber of Aces in Player's Hand DSCThe Dealers Showing Card Hit/Stay +1 = Hit, -1 = Stay: Opposite of Hit/Stay from Hand History if the player lost Feature Set Bet Amount Ace The number of cards remaining in the deck for each value of card 2 … 10 CC Calculated Card Count: Hi-Opt II used Bet Min/Max +1.5 if hand was Black Jack, +1 if won, -1 if lost = Classification

Example of 5 nearest neighbors Neighbors sum to +3, so decide to Hit

Computer started with no knowledge The player gained advantage over dealer using 10 nearest neighbors

Computer simulated three players playing 1000 hands Computer started with large feature set from 5000 hands