Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

7

GAMEON
2001

favoriteEmaildiscussreport

102views Modeling And Simulation» more GAMEON 2001»

A Learning Architecture for the Game of Go

13 years 5 months ago

A Learning Architecture for the Game of Go

Download www.kbs.twi.tudelft.nl

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 ts. 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

A. B. Meijer

Real-time Traffic

Combinatorial Games | GAMEON 2001 | GAMEON 2007 | Human-like Reasoning Ts | Partial Ordering |

claim paper

Related Content

» Temporal Difference Learning of Position Evaluation in the Game of Go

» Evaluation in Go by a Neural Network using Soft Segmentation

» Evolving a Roving Eye for Go

» Learning Opening Strategy in the Game of Go

» Bayesian pattern ranking for move prediction in the game of Go

» Modelling Uncertainty in the Game of Go

» Reinforcement Learning of Local Shape in the Game of Go

» Learning to Estimate Potential Territory in the Game of Go

» Learning to Score Final Positions in the Game of Go

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2001
Where	GAMEON
Authors	A. B. Meijer

Comments (0)