Creating Optimal Multi- Layer Perceptron Networks to play Go with a Genetic Algorithm a.k.a. big Name, Run long time By Nathan Erickson ECE539 Final Proj.

Slides:



Advertisements
Similar presentations
Artificial Intelligence Presentation
Advertisements

1 Neural networks. Neural networks are made up of many artificial neurons. Each input into the neuron has its own weight associated with it illustrated.
Tetris – Genetic Algorithm Presented by, Jeethan & Jun.
Scott Wiese ECE 539 Professor Hu
On the Genetic Evolution of a Perfect Tic-Tac-Toe Strategy
Click to Continue Project Four Sticks Bye Bye Pillow Games Producer / Stacie Rajkovics Lead Developer/ Sota Ogo Developer and Assistant Designer / Joseph.
Playing Tic Tac Toe with Neural Networks Justin Herbrand CS/ECE/ME 539.
Minimax and Alpha-Beta Reduction Borrows from Spring 2006 CS 440 Lecture Slides.
Goal Setting Lawrence Fine Conducted by
Introduction to Cryptography and Security Mechanisms: Unit 5 Theoretical v Practical Security Dr Keith Martin McCrea
Game Design and Programming. Objectives Classify the games How games are design How games are implemented What are the main components of a game engine.
AMAZEing Maze Requirements Elicitation, Modeling, and Analysis Presentation.
MAE 552 – Heuristic Optimization Lecture 28 April 5, 2002 Topic:Chess Programs Utilizing Tree Searches.
Evolution and Coevolution of Artificial Neural Networks playing Go Thesis by Peter Maier, Salzburg, April 2004 Additional paper used Computer Go, by Martin.
Multi Layer Perceptrons (MLP) Course website: The back-propagation algorithm Following Hertz chapter 6.
Graphical Games Kjartan A. Jónsson. Nash equilibrium Nash equilibrium Nash equilibrium N players playing a dominant strategy is a Nash equilibrium N players.
Neural Networks Slides by Megan Vasta. Neural Networks Biological approach to AI Developed in 1943 Comprised of one or more layers of neurons Several.
CORE MECHANICS. WHAT ARE CORE MECHANICS? Core mechanics are the heart of a game; they generate the gameplay and implement the rules. Formal definition:
Check it out! : Simple Random Sampling. Players of a dice game roll five dice and earn points according to the combinations of numbers they roll.
Young Leaders’ Training Game on! (Module E). Brentwood Explorer Scouts Young Leaders’ Training E – Game on! Aim To give you a good understanding of the.
UWECE 539 Class Project Engine Operating Parameter Optimization using Genetic Algorithm ECE 539 –Introduction to Artificial Neural Networks and Fuzzy Systems.
Go An ancient Oriental board game Andrew Simons. Introduction 2 player game of skill. Popular in the Far East, growing in the West. Simple rules, extremely.
Introduction to AI Michael J. Watts
Senior Project – Computer Science – 2015 Modelling Opponents in Board Games Julian Jocque Advisor – Prof. Rieffel Abstract Modelling opponents in a game.
In this chapter we introduce the idea of what it means for something to be truly random. We also investigate techniques for simulating randomness.
C. Benatti, 3/15/2012, Slide 1 GA/ICA Workshop Carla Benatti 3/15/2012.
Soft Computing Lecture 18 Foundations of genetic algorithms (GA). Using of GA.
Upper Confidence Trees for Game AI Chahine Koleejan.
Othello Artificial Intelligence With Machine Learning
Multi-Layer Perceptrons Michael J. Watts
Neural Networks AI – Week 23 Sub-symbolic AI Multi-Layer Neural Networks Lee McCluskey, room 3/10
Computer Go : A Go player Rohit Gurjar CS365 Project Proposal, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Probability (Grade 12) Daljit Dhaliwal. Sticks and Stones game.
 Summary  How to Play Go  Project Details  Demo  Results  Conclusions.
Section 3.1: Proof Strategy Now that we have a fair amount of experience with proofs, we will start to prove more difficult theorems. Our experience so.
Design of a real time strategy game with a genetic AI By Bharat Ponnaluri.
Presenter: Chih-Yuan Chou GA-BASED ALGORITHMS FOR FINDING EQUILIBRIUM 1.
CodeVita Season III (2014 – 2015 Season).
Connect Four AI Robert Burns and Brett Crawford. Connect Four  A board with at least six rows and seven columns  Two players: one with red discs and.
Analysis of algorithms Analysis of algorithms is the branch of computer science that studies the performance of algorithms, especially their run time.
Yan Carlo Rodriguez ECE 3551 Final Project.  To make a program that will change the person voice when using the microphone.  Make the LEDs turn on when.
Computer Go : A Go player Rohit Gurjar CS365 Project Presentation, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Games. Adversaries Consider the process of reasoning when an adversary is trying to defeat our efforts In game playing situations one searches down the.
Machine Learning for an Artificial Intelligence Playing Tic-Tac-Toe Computer Systems Lab 2005 By Rachel Miller.
Introduction to Machine Learning Kamal Aboul-Hosn Cornell University Chess, Chinese Rooms, and Learning.
CSC Intro. to Computing Lecture 22: Artificial Intelligence.
Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter.
Learning Othello The quest for general strategy building.
PhD Projects Rahul Santhanam University of Edinburgh.
DEEP RED An Intelligent Approach to Chinese Checkers.
Intelligent Database Systems Lab 國立雲林科技大學 National Yunlin University of Science and Technology 1 Evolving Reactive NPCs for the Real-Time Simulation Game.
Today’s Topics Playing Deterministic (no Dice, etc) Games –Mini-max –  -  pruning –ML and games? 1997: Computer Chess Player (IBM’s Deep Blue) Beat Human.
Parallelization in Computer Board Games Ian Princivalli.
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
If you would like to play „ T he K ing” you must have: a ball, a big wall and two or more p layers.
Announcements Finish up Network Flow today Then Review for Final on Monday ◦ HW#5 is due on Monday, let me or the TA’s know if you have trouble starting.
Artificial Neural Networks (ANN). Artificial Neural Networks First proposed in 1940s as an attempt to simulate the human brain’s cognitive learning processes.
Othello Artificial Intelligence With Machine Learning Computer Systems TJHSST Nick Sidawy.
The Standard Genetic Algorithm Start with a “population” of “individuals” Rank these individuals according to their “fitness” Select pairs of individuals.
Approaches Workbook Conditioned Games – Teacher Answers.
Teaching Computers to Think:
Neural networks.
Neural Networks Dr. Peter Phillips.
Training a Neural Network
of the Artificial Neural Networks.
CIS 488/588 Bruce R. Maxim UM-Dearborn
AirBnB Pricing Predictions
Lecture 04: Multilayer Perceptron
Evolutionary Algorithms for Hyperparameter Optimization
Outline Announcement Neural networks Perceptrons - continued
Presentation transcript:

Creating Optimal Multi- Layer Perceptron Networks to play Go with a Genetic Algorithm a.k.a. big Name, Run long time By Nathan Erickson ECE539 Final Proj 12/18/03

Go The ancient Chinese game of Go has long been a difficult problem for computer programmers. Its complex and rapidly changing game play makes it very difficult for computers to get a handle on how to play well.

According to the book “The way to go” “The situations that arise from the simple objectives of go are complex enough to have thwarted all attempts to program a competitive go-playing computer. Informed opinion doubts that a computer will soon, if ever, challenge the ability of a go professional. Effective go strategy is sublimely subtle.”

Program Structure and Classes GoArena  Contains the Genetic Algorithm | |-  PopulationManager | | | |  Player  Contains the MLP || ||-  Neuron | |-  GoBoard

The Genetic Algorithm A simple form of the GA is employed in GoArena. Its current function is simply 1. Kill any player that can not win any games 2. Kill the weakest players to make room for more 3. Create a new player with randomly chosen values. 4. Repeat

The MLP The network in GoArena is a fully forward connected network. The network in GoArena is a fully forward connected network. There is no upward bound on the size of the network. There is no upward bound on the size of the network. MLP Reasonableness is ensured by the Genetic Algorithm. MLP Reasonableness is ensured by the Genetic Algorithm. Learns after each game. Learns after each game.

Runtime Using a 9x9 board Using a 9x9 board 1000 generations 1000 generations 1000 Games each 1000 Games each With 100 Players With 100 Players on a Athlon XP on a Athlon XP Takes 12 hours Takes 12 hours Got a supercomputer handy, anyone? Got a supercomputer handy, anyone?

Results At the start the computer is horribly stupid. At the start the computer is horribly stupid. It just places stones in random places. It just places stones in random places. Later in the simulation you can see it has developed the ability to cover the board and group stones for safety. Later in the simulation you can see it has developed the ability to cover the board and group stones for safety. Also later in the simulation you see less players being killed for not being able to win any games. Also later in the simulation you see less players being killed for not being able to win any games.