Backgammon Group 1: - Remco Bras - Tim Beyer - Maurice Hermans - Esther Verhoef - Thomas Acker.

Slides:



Advertisements
Similar presentations
1 Machine Learning: Lecture 1 Overview of Machine Learning (Based on Chapter 1 of Mitchell T.., Machine Learning, 1997)
Advertisements

Todd W. Neller Gettysburg College
Multilayer Perceptrons 1. Overview  Recap of neural network theory  The multi-layered perceptron  Back-propagation  Introduction to training  Uses.
Outline Dudo Rules Regret and Counterfactual Regret Imperfect Recall Abstraction Counterfactual Regret Minimization (CFR) Difficulties Fixed-Strategy.
10/29/01Reinforcement Learning in Games 1 Colin Cherry Oct 29/01.
Playing Tic Tac Toe with Neural Networks Justin Herbrand CS/ECE/ME 539.
2002/11/15Game Programming Workshop1 A Neural Network for Evaluating King Danger in Shogi Reijer Grimbergen Department of Information Science Saga University.
Reinforcement Learning for the Soccer Dribbling Task Arthur Carvalho Renato Oliveira.
The Implementation of Artificial Intelligence and Temporal Difference Learning Algorithms in a Computerized Chess Programme By James Mannion Computer Systems.
Evolutionary Computation For Backgammon david gabai.
CS AI Practicum Fall Robot Downey Jr Will Kiffer Joey Staehle Andrew Bunyea.
Probability CSE 473 – Autumn 2003 Henry Kautz. ExpectiMax.
Modular Neural Networks CPSC 533 Franco Lee Ian Ko.
Blackjack as a Test Bed for Learning Strategies in Neural Networks A. Perez-Uribe and E. Sanchez Swiss Federal Institute of Technology IEEE IJCNN'98.
Reinforcement Learning
Incorporating Advice into Agents that Learn from Reinforcement Presented by Alp Sardağ.
Temporal Difference Learning Versus Co-Evolution for Acquiring Othello Position Evaluation Simon M. Lucas Computer Science Dept, University of Essex Thomas.
SE367 Project Final Presentation By: Sujith Thomas Parimi Krishna Chaitanya In charge:- Prof Amitabha Mukerjee.
GoogolHex CS4701 Final Presentation Anand Bheemarajaiah Chet Mancini Felipe Osterling.
CSC 412: AI Adversarial Search
Machine Learning Chapter 13. Reinforcement Learning
Reinforcement Learning
Temporal Difference Learning By John Lenz. Reinforcement Learning Agent interacting with environment Agent receives reward signal based on previous action.
Introduction Many decision making problems in real life
Computer Go : A Go player Rohit Gurjar CS365 Project Proposal, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Appendix B: An Example of Back-propagation algorithm
Learning BlackJack with ANN (Aritificial Neural Network) Ip Kei Sam ID:
Evaluation Function in Game Playing Programs M1 Yasubumi Nozawa Chikayama & Taura Lab.
Created By: Kevin Jiang, Cullen Wong, Stephen Halter.
Othello Playing AI Matt Smith. Othello 8x8 Board game 8x8 Board game Try to outflank opponents pieces Try to outflank opponents pieces Winner ends up.
1 Phase II - Checkers Operator: Eric Bengfort Temporal Status: End of Week Five Location: Phase Two Presentation Systems Check: Checkers Checksum Passed.
Computer Go : A Go player Rohit Gurjar CS365 Project Presentation, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Introduction to Machine Learning Kamal Aboul-Hosn Cornell University Chess, Chinese Rooms, and Learning.
1 CS 4701 – Project Proposal Jane Park (jp624) Ran Zhao (rz54)
Reinforcement Learning Ata Kaban School of Computer Science University of Birmingham.
2 Digit Divisors. 3,521 ÷ 26 = = 26 x = 26 x 3 Click the squirrel for a video on repeated multiplication.
CHECKERS: TD(Λ) LEARNING APPLIED FOR DETERMINISTIC GAME Presented By: Presented To: Amna Khan Mis Saleha Raza.
Jack Chen TJHSST Computer Systems Lab Abstract The purpose of this project is to explore Artificial Intelligence techniques in the board game.
Game Theory, Social Interactions and Artificial Intelligence Supervisor: Philip Sterne Supervisee: John Richter.
Music Genre Classification Alex Stabile. Example File
Blondie24 Presented by Adam Duffy and Josh Hill. Overview Introduction to new concepts Design of Blondie24 Testing and results Other approaches to checkers.
Carla P. Gomes CS4700 CS 4701: Practicum in Artificial Intelligence Carla P. Gomes
DEEP RED An Intelligent Approach to Chinese Checkers.
1 Let’s play snooker Group 2 Yannick Thimister Frans van den Heuvel Enno Ruijters Esther Verhoef Ali B. Ozmen Achim Leydecker.
SAL: A Game Learning Machine Joel Paulson & Brian Lanners.
The Implementation of Artificial Intelligence and Temporal Difference Learning Algorithms in a Computerized Chess Program By James Mannion Computer Systems.
Reinforcement Learning AI – Week 22 Sub-symbolic AI Two: An Introduction to Reinforcement Learning Lee McCluskey, room 3/10
Reinforcement Learning and Tetris Jared Christen.
CS 5751 Machine Learning Chapter 13 Reinforcement Learning1 Reinforcement Learning Control learning Control polices that choose optimal actions Q learning.
Backgammon: A Concise Description of How to Play this Classic Board Game.
Supervise Learning Introduction. What is Learning Problem Learning = Improving with experience at some task – Improve over task T, – With respect to performance.
Understanding AlphaGo. Go Overview Originated in ancient China 2,500 years ago Two players game Goal - surround more territory than the opponent 19X19.
Stochastic tree search and stochastic games
5.1 Mensch ärgere Dich nicht (Engl. Ludo)
RADIAL BASIS FUNCTION NEURAL NETWORK DESIGN
Reinforcement Learning
Mastering the game of Go with deep neural network and tree search
Backgammon project Oren Salzman Guy Levit Instructors:
CSE 473 Introduction to Artificial Intelligence Neural Networks
Training Neural networks to play checkers
Convolutional Neural Networks
Training a Neural Network
Cache Replacement Scheme based on Back Propagation Neural Networks
network of simple neuron-like computing elements
Neural Networks Chapter 5
Reinforcement Learning for Adaptive Game Learner
Connect 4 Michael Yura.
Word2Vec.
S.N.U. EECS Jeong-Jin Lee Eui-Taik Na
Connect 4 michael yura.
Presentation transcript:

Backgammon Group 1: - Remco Bras - Tim Beyer - Maurice Hermans - Esther Verhoef - Thomas Acker

 Introduction to backgammon  Demonstration  Game complexity  Different AI algorithms  Future plans Overview

 Two players  Pieces are moved according to the roll of dice  One player moves clockwise, other counterclockwise  Pieces kicked off will be placed on the baulk  Scores when reached Home Board Introduction to backgammon

Let’s demonstrate! Demonstration

Game Complexity

 Neural Network ◦ The state of the board as input layer ◦ The evaluation function as hidden layer ◦ The “best move” as output layer AI Algorithms

 Reinforcement Learning (RL) ◦ Learning by playing matches against itself ◦ Temporal Difference Learning (TDL)  Changes after every time step  Temporal  Changes through differences  Difference  Learning of a evaluation (value) function  Learning AI Algorithms

 Pubeval ◦ A benchmark “player” by Gerry Tesauro ◦ Fixed weights  Fixed strategy ◦ Used very often to compare different approaches ◦ Used for illustrating training effects AI Algorithms

 Implement Neural networks  Vary training sessions Future Plans

Week1Week2Week3Week4Week5Week6Week7 Research Implement AI Testing and debugging Improve AI Working on presentation Gannt-Chart