Some Studies in Machine Learning Using the Game of Checkers

  title={Some Studies in Machine Learning Using the Game of Checkers},
  author={Arthur L. Samuel},
  journal={IBM J. Res. Dev.},
  • A. Samuel
  • Published 1959
  • Computer Science
  • IBM J. Res. Dev.
The studies reported here have been concerned with the programming of a digital computer to behave in a way which, if done by human beings or animals, would be described as involving the process of learning. While this is not the place to dwell on the importance of machine-learning procedures, or to discourse on the philosophical aspects,1 there is obviously a very large amount of work, now done by people, which is quite trivial in its demands on the intellect but does, nevertheless, involve… Expand

Figures, Tables, and Topics from this paper

Paper Mentions

A computer model of simple forms of learning in infants
This report presents a computer program, using what I will call an "experience-driven compiler," which is able to program itself to solve a restricted class of problems involving cause-and-effect relationships. Expand
Modeling and designing of machine learning procedures as applied to game playing using artificial intelligence
Modeling and designing of a general learning system is proposed that presents new machine learning procedures used to arrive at "knowledgeable" static evaluators for checker board positions, and these procedures are compared with each other, and with the linear polynomial. Expand
Computers in the study of learning: BOGART—A discovery and induction program for games
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. Expand
Steps toward Artificial Intelligence
  • M. Minsky
  • Computer Science
  • Proceedings of the IRE
  • 1961
The discussion is supported by extensive citation of the literature and by descriptions of a few of the most successful heuristic (problem-solving) programs constructed to date. Expand
Studies in machine cognition using the game of poker
A progress report is presented of on-going research efforts concerning human decision making under uncertainty and risk and human problem solving and learning processes on the one hand, and machineExpand
Learning to learn: An Automated and Continuous Approach to Learning in Imperfect Environments
Our quest to understand, model, and reproduce natural intelligence has opened new avenues of research. One such area is artificial intelligence (AI). AI is the branch of computer science aiming toExpand
On learning and testing evaluation functions
  • B. Abramson
  • Computer Science
  • J. Exp. Theor. Artif. Intell.
  • 1990
This paper reviews the literature concerning techniques for learning and testing static evaluators, and suggests an alternative approach would be to identify a key parameter, to learnevaluators that approximate it, and then to challenge otherwise identical programs with marginally different functions. Expand
Machine learning and games
AI research on computer games began to follow developments in the games industry early on, but since John Laird’s keynote address at the AAAI 2000 conference, numerous workshops, conferences, and special issues of journals demonstrate the growing importance of game-playing applications for Artificial Intelligence. Expand
Distributed Decision Making in Checkers
The aim is to show how the combination of several known models for checkers playing can be integrated into a MADES, that learns how to combine individual decisions, so that the MADES plays better than any of them, without "a priori" knowledge of the quality or area of expertise of each model. Expand
The Layered Learning Method and Its Application to Generation of Evaluation Functions for the Game of Checkers
A Computational Intelligence (CI)-based approach to creating evaluation functions for two player mind games, focusing on development of artificial neural network (ANN)- based heuristics for the game of checkers is described and validated. Expand