Machine Learning for Go

Slides:



Advertisements
Similar presentations
How to Rig Elections and Competitions Noam Hazon*, Paul E. Dunne +, Sarit Kraus*, Michael Wooldridge + + Dept. of Computer Science University of Liverpool.
Advertisements

Game Playing CS 63 Chapter 6
Learning in Computer Go David Silver. The Problem Large state space  Approximately states  Game tree of about nodes  Branching factor.
Martin Boyd Christopher Hirunthanakorn
The Computational Difficulty of Manipulating an Election Tetiana Zinchenko 05/12/
This Segment: Computational game theory Lecture 1: Game representations, solution concepts and complexity Tuomas Sandholm Computer Science Department Carnegie.
Artificial Intelligence in Game Design
Sep. 5, 2013 Lirong Xia Introduction to Game Theory.
Reviewing Prospect Theory According to RCT options should be evaluated in terms of utilities and probabilities. Prospect Theory generalizes about the quantities.
Domineering Solving Large Combinatorial Search Spaces.
The Move Decision Strategy of Indigo Author: Bruno Bouzy Presented by: Ling Zhao University of Alberta March 7, 2007.
Honte, a Go-Playing Program Using Neural Nets Frederik Dahl.
Maximizing the Chance of Winning in Searching Go Game Trees Presenter: Ling Zhao March 16, 2005 Author: Keh-Hsun Chen Accepted by Information Sciences.
Towards Multi-Objective Game Theory - With Application to Go A.B. Meijer and H. Koppelaar Presented by Ling Zhao University of Alberta October 5, 2006.
Games with Chance Other Search Algorithms CPSC 315 – Programming Studio Spring 2008 Project 2, Lecture 3 Adapted from slides of Yoonsuck Choe.
Solving Probabilistic Combinatorial Games Ling Zhao & Martin Mueller University of Alberta September 7, 2005 Paper link:
Learning Shape in Computer Go David Silver. A brief introduction to Go Black and white take turns to place down stones Once played, a stone cannot move.
Reinforcement Learning of Local Shape in the Game of Atari-Go David Silver.
Temperature Discovery Martin M ü ller, Markus Enzenberger and Jonathan Schaeffer zIntroduction: local and global search yLocal search algorithms yTemperature.
Metarules To Improve Tactical Go Knowledge By Tristan Cazenave Presented by Leaf Wednesday, April 28 th, 2004.
Computers Playing Games Arif Zaman CS 101. Acknowledgements Portions of this are taken from MIT’s open-courseware
Choose A Subgame to Play by Zhichao “Leaf” Li October 20th, 2003.
Playing Konane Mathematically with Combinatorial Game Theory
Sum of Combinatorial Games by Leaf Wednesday, October 12th, 2004.
Combinatorial Games Martin Müller. Contents Combinatorial game theory Thermographs Go and Amazons as combinatorial games.
Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.
1 Solving Ponnuki-Go on Small Board Paper: Solving Ponnuki-Go on small board Authors: Erik van der Werf, Jos Uiterwijk, Jaap van den Herik Presented by:
Adversarial Search: Game Playing Reading: Chess paper.
Monte Carlo Go Has a Way to Go Haruhiro Yoshimoto (*1) Kazuki Yoshizoe (*1) Tomoyuki Kaneko (*1) Akihiro Kishimoto (*2) Kenjiro Taura (*1) (*1)University.
1 Recognizing safe territories Presented by: Xiaozhen Niu Date: 2003/09/22.
Reinforcement Learning of Local Shape in the Game of Atari-Go David Silver.
Metagaming General Game PlayingLecture 5 Michael Genesereth Spring 2012.
Game Theory.
Knowledge Acquisition from Game Records Takuya Kojima, Atsushi Yoshikawa Dept. of Computer Science and Information Engineering National Dong Hwa University.
9/14/20151 Game Theory and Game Balance CIS 487/587 Bruce R. Maxim UM-Dearborn.
Introduction Many decision making problems in real life
Othello Artificial Intelligence With Machine Learning
Computer Go : A Go player Rohit Gurjar CS365 Project Proposal, IIT Kanpur Guided By – Prof. Amitabha Mukerjee.
Position Evaluation in Computer Go Martin Muller Dept. of Computer Science and Information Engineering National Dong Hwa University Reporter : Lo Jung-Yun.
Dynamic Games of complete information: Backward Induction and Subgame perfection - Repeated Games -
Solving Hard Instances of FPGA Routing with a Congestion-Optimal Restrained-Norm Path Search Space Keith So School of Computer Science and Engineering.
Relationships Between Structures “→” ≝ “Can be defined in terms of” Programs Groups Proofs Trees Complex numbers Operators Propositions Graphs Real.
Temperature Discovery Search Temperature Discovery Search (TDS) is a new minimaxbased game tree search method designed to compute or approximate the temperature.
Game Playing. Towards Intelligence? Many researchers attacked “intelligent behavior” by looking to strategy games involving deep thought. Many researchers.
W 2 L 1 sh 1 C lessons LessonSubjectBook Week 1 lesson 1Objects, names Week 1 lesson 2Statements, layout Week 2 lesson 1Functions, decomposition Week 2.
Thinking Architecturally An information theory and complex system viewpoint.
Amazons Experiments in Computer Amazons, Martin Mueller and Theodore Tegos, 2002 Exhaustive Search in the Game Amazons Raymond Georg Snatzke, 2002 Presented.
Outline Intro to Representation and Heuristic Search Machine Learning (Clustering) and My Research.
Games as adversarial search problems Dynamic state space search.
Conditional combinatorial games Martin Muller 報告人 : 張歐丞.
IB Computer Science – Logic
Solving Kriegspiel endings with brute force: the case of KR vs. K Paolo Ciancarini Gian Piero Favini University of Bologna.
Strategic Behavior in Business and Econ Static Games of complete information: Dominant Strategies and Nash Equilibrium in pure and mixed strategies.
Learning to Play the Game of GO Lei Li Computer Science Department May 3, 2007.
Solving Tsumego on Computers M2 Hirokazu Ishii Chikayama & Taura Lab.
Knowledge Representation Fall 2013 COMP3710 Artificial Intelligence Computing Science Thompson Rivers University.
Incomplete information: Perfect Bayesian equilibrium
A Scalable Machine Learning Approach to Go Pierre Baldi and Lin Wu UC Irvine.
Introductory Lecture. What is Discrete Mathematics? Discrete mathematics is the part of mathematics devoted to the study of discrete (as opposed to continuous)
Extensive-Form Game Abstraction with Bounds
D1 Miwa Makoto Chikayama & Taura Lab
Mastering the game of Go with deep neural network and tree search
Othello Artificial Intelligence With Machine Learning
Games with Chance Other Search Algorithms
Isolation – Champion Program
CSE (c) S. Tanimoto, 2001 Search-Introduction
Backtracking and Branch-and-Bound
GAMES AND STRATEGIES.
GAMES AND STRATEGIES.
Unit II Game Playing.
Presentation transcript:

Machine Learning for Go Jung-Yun Lo Dept. of computer science and information engineering National Dong Hwa University

Outline A survey of the application of machine learning to the game of Go A learning architecture for the game of Go

A survey Some possible directions of research Global approaches Learning in search Learning in the endgame Learning in the opening The representation language

Global approaches Learning a function from a board position and a move to a reward On large boards, probably a more specific method should be used for different subproblems of the game

Learning in search temperature (high → deeper search) candidate move ordering temperature (low → stop search) Leaf node static evaluation

Learning in the endgame Each local endgame positions is evaluated, then the whole game is considered as a sum of games Decomposition search

Learning in the opening Hard to quantify Using joseki Depend on the surrounding situation Learning a global rules for opening moves

The representation language Difficult to express more high-level concepts such as liberty, atari, ladder and eye Making the representation language more expressive

The representation language block( BlockID, Color, Size, LibertyCount) board( X, Y, GroupID) adjacent( BlockID1, BlockID2)

The representation language

The representation language The Common Fate Graph (Enzenberger, 1996)

The representation language projection projection

The representation language Loss of information in the CFG

Conclusions Learning result are promising, but the whole field is nearly unexplored and much opportunities to do research

A learning architecture for the game of Go Combinatorial Game Theory The HUGO Architecture Three Components of HUGO Choice of Subgames Initiative Engine Computing Game Value

Combinatorial game theory G = {F|O} F : the set of options that player Friend can reach with one legal move O : for player Opponent F can be 2 possible value W : win for Friend L : loss for Friend

Combinatorial game theory 4 possible outcomes for a combinatorial game : WW, WL, LL, and LW WW : won by Friend, irrespective of who moves first WL : an unsettled game, won by the player who moves first LL : lost for Friend even if Friend moves first LW : the player who moves first will loss the game

The HUGO architecture Can be applied to any 2-player, deterministic, full information, partizan, combination game

3 components of HUGO Choice of subgames Initiative engine Select a collection of well-defined subgames Ensure a high discriminative abilities Initiative engine Find the move that yields the most points Prefer holding initiative Computing game values Compute the game-theoretic value of a particular game

Future work Study more reference about machine learning

Reference A Survey of The Application of Machine Learning to The Game of Go Jan Ramon, Hendrik Blockeel / Katholieke Univ. Leuven A Learning Architecture for The Game of Go A.B. Meijer, H. Koppelaar / Delft Univ. of tech. Computer Go and Machine Learning Thore Graepal http://bbs2.xilubbs.com/cgi-bin/bbs/view?forum=godknows&message=105