Computational Intelligence: Some Insights from Board Games Fernand Gobet Brunel University.

Slides:



Advertisements
Similar presentations
Adversarial Search Chapter 6 Sections 1 – 4. Outline Optimal decisions α-β pruning Imperfect, real-time decisions.
Advertisements

Additional Topics ARTIFICIAL INTELLIGENCE
Adversarial Search Chapter 6 Section 1 – 4. Types of Games.
AI for Connect-4 (or other 2-player games) Minds and Machines.
Introduction to Artificial Intelligence (40-417).
Adversarial Search Chapter 5.
COMP-4640: Intelligent & Interactive Systems Game Playing A game can be formally defined as a search problem with: -An initial state -a set of operators.
"Programming a Computer to Play Chess" A presentation of C. Shannon's 1950 paper by Andrew Oldag April
Artificial Intelligence AI: The branch of computer science dedicated to the creation of machines that perform task which if done by humans would be considered.
The Implementation of Artificial Intelligence and Temporal Difference Learning Algorithms in a Computerized Chess Programme By James Mannion Computer Systems.
Artificial Intelligence for Games Game playing Patrick Olivier
Games as a Test Bed for Developing AI Applications (in Physics) Brains vs Computers Symposium of the “van der Waals” study association December 10, 2013.
An Introduction to Artificial Intelligence Lecture VI: Adversarial Search (Games) Ramin Halavati In which we examine problems.
1 Adversarial Search Chapter 6 Section 1 – 4 The Master vs Machine: A Video.
Games CPSC 386 Artificial Intelligence Ellen Walker Hiram College.
By Joseph Tanti FIDE Instructor. Some completely different ways to play chess.
Introduction to AI Kaziwa H. Saleh. What is AI? John McCarthy defines AI as “the science and engineering to make intelligent machines”. AI is the study.
An Introduction to Artificial Intelligence. Introduction Getting machines to “think”. Imitation game and the Turing test. Chinese room test. Key processes.
Game Playing in the Real World Oct 8 th : Uncertainty and Probabilistic reasoning Oct 10th: How should we define artificial intelligence? Reading for Oct.
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering CSCE 580 Artificial Intelligence Ch.6: Adversarial Search Fall 2008 Marco Valtorta.
What is AI  An attempt to imitate human reactions by scripting reactions to happen when a certain cause is brought about.
Random Administrivia In CMC 306 on Monday for LISP lab.
double AlphaBeta(state, depth, alpha, beta) begin if depth
Artificial Intelligence Instructor: Professor Yun Peng
Computer Chess. Humble beginnings The Turk Ajeeb Mephisto El Ajedrecista.
Group 1 : Ashutosh Pushkar Ameya Sudhir From. Motivation  Game playing was one of the first tasks undertaken in AI  Study of games brings us closer.
Games. The Turk Built by Wolfgang von Kempelen (1734 – 1804).
Game Playing State-of-the-Art  Checkers: Chinook ended 40-year-reign of human world champion Marion Tinsley in Used an endgame database defining.
Chapter 13: Is Artificial Intelligence Real?
Introduction to AI, H. Feili 1 Introduction to Artificial Intelligence LECTURE 1: Introduction What is AI? Foundations of AI The.
CPSC 171 Artificial Intelligence Read Chapter 14.
ARTIFICIAL INTELLIGENCE Introduction: Chapter 1. Outline Course overview What is AI? A brief history The state of the art.
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.
Artificial Intelligence in Game Design Problems and Goals.
Chapter 16 Can Computers Think (now or in the future)? Can Computers Think (now or in the future)?
Introduction: Chapter 1
Artificial Intelligence
Introduction to Machine Learning MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way Based in part on notes from Gavin Brown, University of Manchester.
Artificial Intelligence
Development of a Machine-Learning-Based AI For Go By Justin Park.
Projects Analyze Existing Game project –Due next class. Re-check the guidelines on course’s website! Create your Own Project –Due: Final game due Tuesday.
Adversarial Search Chapter 6 Section 1 – 4. Outline Optimal decisions α-β pruning Imperfect, real-time decisions.
Introduction to Artificial Intelligence CS 438 Spring 2008 Today –AIMA, Ch. 6 –Adversarial Search Thursday –AIMA, Ch. 6 –More Adversarial Search The “Luke.
Game Playing. Towards Intelligence? Many researchers attacked “intelligent behavior” by looking to strategy games involving deep thought. Many researchers.
The Mind of the Machine: Artificial Intelligence? Paul Curzon Queen Mary, University of London Created by Peter McOwan and Paul Curzon of Queen Mary,
1 Adversarial Search CS 171/271 (Chapter 6) Some text and images in these slides were drawn from Russel & Norvig’s published material.
CHAPTER 4 PROBABILITY THEORY SEARCH FOR GAMES. Representing Knowledge.
Backtracking and Games Eric Roberts CS 106B January 28, 2013.
Definitions of AI There are as many definitions as there are practitioners. How would you define it? What is important for a system to be intelligent?
CSE373: Data Structures & Algorithms Lecture 23: Intro to Artificial Intelligence and Game Theory Based on slides adapted Luke Zettlemoyer, Dan Klein,
Game tree search Chapter 6 (6.1 to 6.3 and 6.6) cover games. 6.6 covers state of the art game players in particular. 6.5 covers games that involve uncertainty.
The Implementation of Artificial Intelligence and Temporal Difference Learning Algorithms in a Computerized Chess Program By James Mannion Computer Systems.
Artificial Intelligence
Artificial Intelligence Past, Present, & Future Andrea McGrath April 21 st, 2006.
FOUNDATIONS OF ARTIFICIAL INTELLIGENCE
Explorations in Artificial Intelligence Prof. Carla P. Gomes Module 5 Adversarial Search (Thanks Meinolf Sellman!)
Adversarial Search Chapter 5 Sections 1 – 4. AI & Expert Systems© Dr. Khalid Kaabneh, AAU Outline Optimal decisions α-β pruning Imperfect, real-time decisions.
ADVERSARIAL SEARCH Chapter 6 Section 1 – 4. OUTLINE Optimal decisions α-β pruning Imperfect, real-time decisions.
CPSC 121: Models of Computation REVIEW. Course Learning Outcomes You should be able to: – model important problems so that they are easier to discuss,
Game Playing Why do AI researchers study game playing?
Videos NYT Video: DeepMind's alphaGo: Match 4 Summary: see 11 min.
Adversarial Search Chapter 5.
Dakota Ewigman Jacob Zimmermann
Adversarial Search.
The intelligent piece of paper: so what is an algorithm?
Artificial Intelligence introduction(2)
Mini-Max search Alpha-Beta pruning General concerns on games
Introduction to Artificial Intelligence
Adversarial Search Chapter 6 Section 1 – 4.
Presentation transcript:

Computational Intelligence: Some Insights from Board Games Fernand Gobet Brunel University

Board Games Seems a good choice Both humans and machines are good at them But with different approaches Has attracted the interest of some of the giants of computer science: Alan Turing Claude Shannon Herbert Simon John Holland

Brute Force May Lead to Intelligence, after All Humans, including world champions, search highly selectively Kasparov probably searches at most 10 positions in a minute In 1997, Deep Blue beat Kasparov using massive search (200 mio positions per sec) But similar approaches have failed in Go

Is Parsimony Critical? Research into chess suggests that grandmasters have hundreds of thousands of perceptual patterns and rules With algorithms such as C4.5, decision trees with more than dozens of nodes are seen as too large

How Much Knowledge? Human masters typically use a lot of knowledge Acquired by instruction, study, and experience Many computational systems use little domain-specific knowledge Bottom up induction of knowledge (rules, clusters, etc.)

Problem-Based Learning Humans often learn while solving problems -- e.g., playing games Many computational techniques passively learn by accessing information in databases Does this affect the quality of what is being learnt? Later performance?

Bounded Rationality and Optimality Humans typically learn and behave in a sub-optimal way--but in real-time Their knowledge is not structured optimally (e.g., presence of contradictions) Similar flavour with biological evolution and Microsoft software Many CI techniques aim at optimal learning Is this realistic?