Computers in the study of learning: BOGART—A discovery and induction program for games

Authors:
C. Newman;L. Uhr
Affiliations:
-;-
Venue:
ACM '65 Proceedings of the 1965 20th national conference
Year:
1965

Citing 3
Cited 2

Chess-playing programs and the problem of complexity

Computers & thought
Realization of a geometry-theorem proving machine

Computers & thought
A pattern-recognition program that generates, evaluates, and adjusts its own operators

Computers & thought

Constructive induction on decision trees

IJCAI'89 Proceedings of the 11th international joint conference on Artificial intelligence - Volume 1
Mikrokosms and robots

IJCAI'69 Proceedings of the 1st international joint conference on Artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

BOGART consists of a set of board game playing routines written in MAD (Michigan Algorithm Decoder) which is capable of learning to play board games. Examples of board games BOGART can learn to play, with widely varying degrees of proficiency, include Tic-Tac-Toe, hexapawn, GOMOKU, and checkers, and it can solve missionary and cannibal problems. The objective in constructing BOGART is to illustrate that it is possible to solve a large class of dissimilar problems by the use of learning techniques. Proficiency at solving any one problem was not an objective, nor was general proficiency that did not depend on the use of learning. Consistent with this philosophy of relying on learning techniques, no use is made of lookahead procedures, although they have been shown to be of great value in game-playing programs.