Book ChapterDOI
Backgammon Computer Program Beats World Champion
Reads0
Chats0
TLDR
This paper examines the scientific issues involved in constructing the program, an analysis of its performance, and the scientific significance of the win and presents the SNAC method of constructing evaluation functions.About:
This article is published in Artificial Intelligence.The article was published on 1980-09-01. It has received 82 citations till now. The article focuses on the topics: Champion.read more
Citations
More filters
Book
The knowledge level
TL;DR: A theory of the nature of knowledge is proposed, namely, that there is another computer system level immediately above the symbol (or program) level and knowledge itself is the processing medium at this level and the principle of rationality plays a central role.
Journal ArticleDOI
The knowledge level
TL;DR: In this article, a theory of the nature of knowledge and representation is proposed, namely that there is another computer system level immediately above the symbol (or program) level, and the principle of rationality plays a central role.
Book
Superintelligence: Paths, Dangers, Strategies
TL;DR: In this paper, Bostrom's work picks its way carefully through a vast tract of forbiddingly difficult intellectual terrain, and the writing is so lucid that it somehow makes it all seem easy.
Book ChapterDOI
K*: An Instance-based Learner Using an Entropic Distance Measure
TL;DR: K*, an instance-based learner that uses entropy as a distance measure, is described, and results that compare favourably with several machine learning algorithms are presented.
References
More filters
Journal ArticleDOI
Some studies in machine learning using the game of checkers
TL;DR: In this article, two machine learning procedures have been investigated in some detail using the game of checkers, and enough work has been done to verify the fact that a computer can be programmed so that it will lear...
Journal ArticleDOI
Some studies in machine learning using the game of checkers. II: recent progress
TL;DR: Full use is made of the so called "alpha-beta" pruning and several forms of forward pruning to restrict the spread of the move tree and to permit the program to look ahead to a much greater depth than it otherwise could do.
Proceedings Article
Some necessary conditions for a master chess program
TL;DR: The outline of a model of chess playing that avoids the Horizon Effect and appears extendable to play Master level chess is presented, together with some results already achieved.
Proceedings Article
On the construction of evaluation functions for large domains
TL;DR: It is shown how to create sensitive evaluation functions and how to avoid stability problems in non-linear functions and two effects, not previously found in the literature: the suicide construction, and the blemish effect.