Computer Go: Knowledge, Search, and Move Decision

@article{Chen2001ComputerGK,
  title={Computer Go: Knowledge, Search, and Move Decision},
  author={Keh-Hsun Chen},
  journal={J. Int. Comput. Games Assoc.},
  year={2001},
  volume={24},
  pages={203-215}
}
  • Keh-Hsun Chen
  • Published 2001
  • Computer Science
  • J. Int. Comput. Games Assoc.
This paper intends to provide an analytical overview of the research performed in the domain of computer Go. Domain knowledge that is essential to Go-playing programs is identified. Various computation and search techniques that can be used effectively to obtain helpful domain knowledge are presented. Four different move-decision paradigms applied by today’s leading Go programs are discussed. Conclusions are drawn and two proposals of improvements to current move-decision paradigms are… 

Figures and Tables from this paper

Monte-Carlo Tree Search and Computer Go

TLDR
This chapter gives an overview of both classical and MCTS approaches to computer Go, bringing an exciting breakthrough in computer Go toward challenging human experts, especially on smaller Go boards.

A New Heuristic Search Algorithm for Capturing Problems in Go

TLDR
A highly selective heuristic search algorithm that solved most capturing problems in Kano's four volumes of graded Go problems and is fast enough to be used by Go programs in real time.

The Move-Decision Strategy of Indigo

  • B. Bouzy
  • Economics
    J. Int. Comput. Games Assoc.
  • 2003
TLDR
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.

A Small Go Board Study of Metric and Dimensional Evaluation Functions

  • B. Bouzy
  • Computer Science
    Computers and Games
  • 2002
TLDR
This paper defines very-little-knowledge evaluation functions used by programs playing on very small boards, based on two mathematical tools, distance and dimension, and not on domain-dependent knowledge.

Computer Go and Monte Carlo Tree Search: Opening Book and Parallel Solutions

TLDR
A method to guide a Monte Carlo Tree Search in the initial moves of the game of Go, which matches the current state of a Go board against clusters of board configurations that are derived from a large number of games played by experts.

Monte-carlo tree search with heuristic knowledge: a novel way in solving capturing and life and death problems in go

Monte-Carlo (MC) tree search is a new research field. Its effectiveness in searching large state spaces, such as the Go game tree, is well recognized in the computer Go community. Go domain-specific

Learning to Estimate Potential Territory in the Game of Go

This paper investigates methods for estimating potential territory in the game of Go. We have tested the performance of direct methods known from the literature, which do not require a notion of life

References

SHOWING 1-10 OF 38 REFERENCES

Computer Go: An AI oriented survey

A1 techniques used in Computer Go

TLDR
This paper surveys the most competitive Computer Go programs, and summarises the AI techniques used, key challenges that must be faced, and issues involved in game tree search, showing why Computer Chess techniques do not translate well to the Go domain.

Forward Pruning and Other Heuristic Search Techniques in Tsume Go

B Probability Based Search

Lambda-Search in Game Trees - with Application to Go

This paper proposes a new method for searching two-valued (binary) game trees in games like chess or Go. Lambda-search uses null-moves together with different orders of threat-sequences (so-called

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

TLDR
Methods for integrating expert Go knowledge into a learning artiicial neural network are implemented in the program NeuroGo, which is able to achieve a playing strength which is equal to a conventional program playing at a medium level.

A study of decision error in selective game tree search

Smart game board and go explorer: a study in software and knowledge engineering

TLDR
The experimental nature of knowledge engineering goes hand-in-hand with a style of software development best characterized as ‘exploratory,’ which has not been much studied in traditional software engineering.

Mean and Temperature Search for Go Endgames

  • K. Kao
  • Computer Science
    Inf. Sci.
  • 2000