Angel \”Java\” Lopez on Blog

May 8, 2012

Computer Go: Links, News And Resources (2)

Filed under: Artificial Intelligence, Computer Go, Game Development, Links — ajlopez @ 4:16 pm

Previous Post

More links about this hard problem in Artificial Intelligence: play the game of Go.

In an Ancient Game, Computing’s Future
EARLY in the film ”A Beautiful Mind,” the mathematician John Nash is seen sitting in a Princeton courtyard, hunched over a playing board covered with small black and white pieces that look like pebbles. He was playing Go, an ancient Asian game. Frustration at losing that game inspired the real Mr. Nash to pursue the mathematics of game theory, research for which he eventually won a Nobel Prize.

What’s black, white and can stump computers?

Handicap for smaller board sizes

Two Representative Computer Go Games

Database pattern search software

Number of legal Go positions

Zen computer Go program beats Takemiya Masaki with just 4 stones!

Orego is a multi-year project to develop programs to play the classical Asian game of Go.

ICGA Tournaments
Tournaments between computer programs: chess, draughts, checkers, Go, backgammon, and more

Moyoman is an open-source Go playing program written in Java. The code for move generation is broken up into units called modules. The interfaces for these modules are well-defined, and correspond to standard Go concepts such as shape, the opening, or life and death. There can be multiple implementations of the same module type. The idea is to distribute the design decisions among many different developers. We are actively looking for new developers to write modules.

Computer Go Group at University of Alberta

Computer Go Bibliography

Fuego, GNU Go and other builds for Windows

Computer Go Research
Our Go program and framework Fuego. First computer program to win a 9×9 game on even against a top-ranked human player.

Monte Carlo Tree Search
Monte Carlo Tree Search (MCTS) is the basis of all state of the art Go programs, including Fuego. In our research, we also investigate Monte Carlo techniques in planning, and the close connections between Reinforcement learning and MCTS.

Latest Advance in Artificial Intelligence: Computer Wins a Game Against a Go Master

Cracking GO
Brute-force computation has eclipsed humans in chess, and it could soon do the same in this ancient Asian game

GoGui is a graphical user interface to programs that play the board game Go and support the Go Text Protocol such as GNU Go.

MoGo: a Grid5000-based software for the Game of Go

The Game of Go: A Programmer’s Perspective

Go news and sensations

Windows HPC: Playing GO on Surface against a Cluster

GTP engines
A go engine is a software that plays go. A GTP go engine is a software that plays go and dialogs through the "Go Text Protocol" with another software like GoGui or Dariush.

Dutch Supercomputer Beats Human at Go

Smart Games

My Links

Keep tuned!

Angel “Java” Lopez

May 3, 2012

Computer Go: Links, News and Resources (1)

Filed under: Artificial Intelligence, Computer Go, Game Development, Links — ajlopez @ 1:17 pm

Next Post

Computer Go is one of my favorites topics. A challenge for game artificial intelligence, the ancient game is enjoyable by itself, and I recommend you to learn how to play it. Some of my links about the topic of computer go:

(citeseer access needs a free account, you must register)

Go (圍棋 weiqi in Chinese, 囲碁 igo in Japanese, 바둑 baduk in Korean, common meaning: “encircling game”), is an ancient board game for two players that originated in China more than 2,000 years ago. The game is noted for being rich instrategy despite its relatively simple rules.

Computer Go is the field of artificial intelligence (AI) dedicated to creating a computer program that plays Go, a traditional board game.

Computer Go
Computer Go is one of the biggest challenges faced by game programmers. This survey describes the typical components of a Go program, and discusses knowledge representation, search methods and techniques for solving specific subproblems in this domain.

Computer Go: an AI Oriented Survey
Since the beginning of AI, mind games have been studied as relevant application fields. Nowadays, some programs are better than human players in most classical games. Their results highlight the efficiency of AI methods that are now quite standard. Such methods are very useful to Go programs, but they do not enable a strong Go program to be built. The problems related to Computer Go require new AI problem solving methods.

Global and Local Game Tree Search

The Move Decision Strategy of Indigo
This paper describes the move decision strategy of Indigo. By using the example of Indigo, the paper shows that the move decision process of a Go program can be very different from the processes used in other games with lower complexity than the complexity of Go, even if the basic modules are conventional (move generator, evaluation function and tree search). Indigo uses them in a specific way, adapted to computer Go, which may be of interest for researchers on other mind games as complex as Go.

Using Hard And Soft Artificial Intelligence Algorithms To Simulate Human Go Playing Techniques

Associating Domain-Dependent Knowledge and Monte Carlo Approaches within a Go Program

Bruno Bouzy Papers

Pursuing abstract goals in the game of Go

A positional Judgment System for Computer Go
Computer Go offers researchers a new challenge and opens up a very wide scope of possibilities for artificial intelligence. In a computer Go program, the most important element is a positional judgment system. Following the methods of human Go experts, we designed and implemented a new model of positional judgment for computer Go.

Value Function
Any strong Computer Go program must compute a win/lose value function as an intermediate step, that corresponds directly to the expected result at the end of the game (win, lose or draw).

The Question Hypothesis
All useful features of a state in Go can be interpreted as answers to questions about the current and future value of observations.

The value-function hypothesis
All efficient methods for solving sequential decision problems determine (learn or compute) value functions as an intermediate step.

Pattern Matching

On Meta-Game Approaches to Computer Go
Meta-game approaches are studied through the design of the Go playing program INDIGO. Computer Go is a challenge for AI and the machine still remains weak compared to humans in the game of Go. This difference is used to try new technics as such as the Metagame technique discussed in this paper. A conceptual structure and a notion of Conway’s game theory are described in order to show four approaches. Each approach is presented to show its method using games, its computational cost, its precision and its Meta-game’s utilisation.

Mathematical Morphology Applied to Computer Go
This paper shows how mathematical morphological operators can be applied to computer go. On one hand, mathematical morphology is a very powerful tool within image processing community. On the other hand, the Zobrist’s model is well-known within the computer go community for its “influence” recognition. We present a model, derived from the closing operator of mathematical morphology and from the Zobrist’s model, which yields very good results for “territory” recognition.

Computer Go
An international bulletin devoted to the generation and exchange of ideas about Computer Go

Computer Go: El gran problema de AI

Computer Go Programming

Computer Go Algorithms

Benson’s Definition of Unconditional Life

MultiGo is designed to view/edit Smart-Go format(SGF) go game file. It also supports other popular file format including *.BDX, *.NGF, *.GOS, *.GIB, *.UGF, *.GO. You can easily navigate through the game and branches, add/remove markers and comments, create or edit your own branches. You could use MultiGo to play with GNU Go, or even record/play go video.

Compendium of Rules for Wei-Qi (Go, Baduk)
GO: An hour to learn; a lifetime to master.

Go Variants
Here are some variants of our noble game, in case you want to do something else.

Computer Go/Writing a Go Engine

BiGo Software

Game Theories and Computer Go

The program GoTools and its computer-generated tsume go database

Forward Pruning and Other Heuristic Search Techniques in Tsume Go

Eyespace Values in Go

The complexity of Go

Computer Go as a Sum of Local Games: An Application of Combinatorial Game Theory

The Integration of A Priori Knowledge into a Go Playing Neural Network

Lambda-Search In Game Trees – With Application To Go

Race to Capture: Analyzing Semeai

Experiments in Computer Go Endgames
Recently, the mathematical theory of games has been applied to late-stage Go endgames [Berlekamp and Wolfe 1994; Wolfe 1991]. Based upon this theory, we developed a tool to solve local Go endgames. We verified all exact game values in [Wolfe 1991] and analyzed some more complex positions. We extended our method to calculate bounds for positions where optimal play depends on Ko. Our program Explorer uses this tool to play full board endgames. It plays a nontrivial class of endgame positions perfectly. In a last section we discuss heuristic play for a wider range of endgames.

Generation of Patterns With External Conditions for the Game of Go

Metarules to Improve Tactical Go Knowledge

Metaprogramming Domain Specific Metaprograms

Tristan Cazenave Articles

Honte, a Go-Playing Program Using Neural Nets

A small Go board Study of metric and dimensional Evaluation Functions
The difficulty to write successful 19×19 go programs lies not only in the combinatorial complexity of go but also in the complexity of designing a good evaluation function containing a lot of knowledge. Leaving these obstacles aside, this paper defines very-little-knowledge evaluation functions used by programs playing on very small boards. The evaluation functions are based on two mathematical tools, distance and dimension, and not on domaindependent knowledge.

The go-playing program called Go81

Developments On Monte Carlo Go

A Learning Architecture For The Game Of Go
In this paper, a three-component architecture of a learning environment for Go is sketched, which can be applied to any two-player, deterministic, full information, partizan, combinatorial game. The architecture called HUGO has natural and human-like reasoning components. Its most abstract component deals with the selection of subgames of Go. The second component is concerned with initiative. The notion of gote no sente (a move that loses initiative but creates new lines of play that will hold initiative) is formalized. In the third component, game values are computed with a new kind of – algorithm based on fuzzy, partial ordering. Our approach leaves some valuable control parameters and oers ways to apply further machine learning techniques.

My Links

More links are coming.

Keep tuned!

Angel “Java” Lopez

Create a free website or blog at