Connect 4 Michael Yura.

Slides:



Advertisements
Similar presentations
ChooseMove=16  19 V =30 points. LegalMoves= 16  19, or SimulateMove = 11  15, or …. 16  19,
Advertisements

Example 4 A National Hockey League team receives 2 points for each win (in regulation time or overtime), 1 point for each loss in overtime, and no points.
Horse race © Horse race: rules 1.Each player chooses a horse and puts it into a stall. Write your name next to the.
Lesson 2-2 Example Solve. Tic Tac Toe Katrina and her friend played Tic Tac Toe. The outcomes of the games are shown in the line plot. Did Katrina.
3.2 Solving by Substitution and Elimination 3.3 Application.
Can you use your clicker? 1. Yes 2. No. Let A = we won the first game, B = we won the second game, and C = we are first in the league. The following sentence.
Jeopardy People DatesEventsCultureTriviaEconomy.
Mathematical Expectation Making the game fair. Make the Bet = X (we need to figure it out) Create the Table Under the column for outcome (O) subtract.
Decision Theory: Outcomes and Consequences Not Considered Decision Outcomes Consequences Decision: choose between betting on green or red chip. Objective:
Probability Distributions. We need to develop probabilities of all possible distributions instead of just a particular/individual outcome Many probability.
DEEP RED An Intelligent Approach to Chinese Checkers.
Well Posed Learning Problems Must identify the following 3 features –Learning Task: the thing you want to learn. –Performance measure: must know when you.
Teaching Computers to Think:
$200 $400 $600 $800 $1000 $200 $400 $600 $800 $1000 $200 $400 $600 $800 $1000 $200 $400 $600 $800 $1000 $200 $400 $600 $800 $1000 $200.
Supervise Learning Introduction. What is Learning Problem Learning = Improving with experience at some task – Improve over task T, – With respect to performance.
Presidential Mania 2-4 players ages 9+ Object: to travel around the board, and reach the White House. Contents: 1 presidential game-board, 4 colorful pieces,
Name 8/29/17.
Minimizing Mistakes Playing against the Captain
Geri’s game EXPOSITION – Geri sits down at a table in the park and sets up chess. MENU INCITING INCIDENT – Nobody is at the park to play chess w/ Geri.
Analyzing Games of Chance Investigation 5 – How Likely Is It?
Writing Expressions Game
Tic-Tac-Throw! How to Play: X or O
Development Snakes and Ladders
Designing: A Game of Chance
Pre-Calculus – Chapter 2
Mastering the game of Go with deep neural network and tree search
THE 5TH QUARTER SPONSORSHIP
Volume: Working Backwards
AlphaGO from Google DeepMind in 2016, beat human grandmasters
نتعارف لنتألف في التعارف تألف (( الأرواح جنود مجندة , ماتعارف منها أئتلف , وماتنافر منها اختلف )) نماذج من العبارات الايجابية.
Reinforcement Learning
Critical Thinking Lecture 14 Pascal’s wager
What did you need to do to play the game?
C nnect 4 Group 9-18 See Zhuo Rui Jorelle 3S3 (Leader)
The Game: Attack and Defend
Game playing.
Attribution Theory Attribution theory looks at the reasons given by coaches and players themselves to account for successes and failures in sport. There.
3.2 Solving by Substitution and Elimination 3.3 Application
COUNTING AND PROBABILITY
CAP 5636 – Advanced Artificial Intelligence
Multi Step Equations 1.) 3a a 2.) 4.3(5.6 + c) + 9c
Linear sequences A linear sequence is a name for a list of numbers where the next number is found by adding or subtracting a constant number. Here is an.
Extra Brownie Points! Lottery To Win: choose the 5 winnings numbers from 1 to 49 AND Choose the "Powerball" number from 1 to 42 What is the probability.
Adding Integers with Different Signs
Game Theory Day 4.
Accuracy Activity: SHAZAM!
Best Strategies For Tennis Game By Amedeo Macchiavelli.
Investigation 3 Making decisions with Probability
Turn off sound Exit Play Game Controls Kanda Productions Presents.
Experimental probability
Lecture 20 Linear Program Duality
A First Grade Number Routine
Addo How to play.
Connect 4 Michael Yura.
Pod # 32 February 6, 2019.
Solving Linear Equations
Try starting with fewer objects to investigate.
Odds.
Solving Harder Linear Equations
Probability in Baseball
Unit 10 Review Around the World.
These neural networks take a description of the Go board as an input and process it through 12 different network layers containing millions of neuron-like.
B B B B K K K K W W W W B B B B G G G G C C C C D D D D L L L L K K K
Accuracy Activity: SHAZAM!
Connect 4 michael yura.
Experimental and Theoretical Probability
PROBABILITY.
Odds and Evens Here is a set of numbered balls used for a game:
Narrative Writing Prompt
Lesson 4.1: Identifying linear functions
Presentation transcript:

connect 4 Michael Yura

what's this all about? create connect 4 create a dynamic ai for connect 4 use reinforcement learning training against other ai's test different “aggressiveness” of learning

ai outline keeps track of the moves it does for each board it is presented with examines if it has won or lost the game changes the way it places pieces in the future depending on the game's outcome (reinforcement learning)‏ if won, will do what it did more often if lost, will do what it did less often

board data 1 [0,0;0][0,1;0][0,2;0][0,3;0][0,4;0][0,5;0][1,0;1][1,1;2][1,2;0][1,3;0][1,4;0][1,5;0][2,0;1][2,1;0][2,2;0][2,3;0][2,4;0][2,5;0][3,0;0][3,1;0][3,2;0][3,3;0][3,4;0][3,5;0][4,0;2][4,1;0][4,2;0][4,3;0][4,4;0][4,5;0][5,0;1][5,1;0][5,2;0][5,3;0][5,4;0][5,5;0][6,0;0][6,1;0][6,2;0][6,3;0][6,4;0][6,5;0] 2 [0,0;0][0,1;0][0,2;0][0,3;0][0,4;0][0,5;0][1,0;1][1,1;2][1,2;0][1,3;0][1,4;0][1,5;0][2,0;1][2,1;1][2,2;2][2,3;0][2,4;0][2,5;0][3,0;1][3,1;0][3,2;0][3,3;0][3,4;0][3,5;0][4,0;2][4,1;1][4,2;2][4,3;0][4,4;0][4,5;0][5,0;1][5,1;2][5,2;1][5,3;1][5,4;0][5,5;0][6,0;2][6,1;2][6,2;0][6,3;0][6,4;0][6,5;0] 3 [0,0;0][0,1;0][0,2;0][0,3;0][0,4;0][0,5;0][1,0;1][1,1;2][1,2;0][1,3;0][1,4;0][1,5;0][2,0;1][2,1;1][2,2;2][2,3;0][2,4;0][2,5;0][3,0;0][3,1;0][3,2;0][3,3;0][3,4;0][3,5;0][4,0;2][4,1;1][4,2;2][4,3;0][4,4;0][4,5;0][5,0;1][5,1;2][5,2;1][5,3;1][5,4;0][5,5;0][6,0;2][6,1;0][6,2;0][6,3;0][6,4;0][6,5;0]

board data 1 [0,0;0][0,1;0][0,2;0][0,3;0][0,4;0][0,5;0][1,0;1][1,1;2][1,2;0][1,3;0][1,4;0][1,5;0][2,0;1][2,1;0][2,2;0][2,3;0][2,4;0][2,5;0][3,0;0][3,1;0][3,2;0][3,3;0][3,4;0][3,5;0][4,0;2][4,1;0][4,2;0][4,3;0][4,4;0][4,5;0][5,0;1][5,1;0][5,2;0][5,3;0][5,4;0][5,5;0][6,0;0][6,1;0][6,2;0][6,3;0][6,4;0][6,5;0]

board

prob data [94.0,15.6,77.2,92.8,100.0,43.3,0.1,]

prob data [94.0,15.6,77.2,92.8,100.0,43.3,0.1,] Total = 423.0 94.0/423.0 (22.22%) chance of placing in Column 1 15.6/423.0 (3.69%) chance of placing in Column 2 77.2/423.0 (18.25%) chance of placing in Column 3 92.8/423.0 (21.94%) chance of placing in Column 4 100.0/423.0 (23.64%) chance of placing in Column 5 43.3/423.0 (10.27%) chance of placing in Column 6 0.1/423.0 (0.02%) chance of placing in Column 7

looking ahead to 4rd quarter program ai to change its %'s depending on whether it wins or loses All %’s are changed equally (constant)‏ %’s toward the end of the game are changed more than toward the beginning (linear)‏ does an ai that is more “aggressive” (changes its %'s to a greater degree each time) learn to play better? Store data in spreadsheets Can an ai train itself?