From Simple Features to Sophisticated Evaluation Functions

Lecture notes in computer sciencePublished 1 January 1999

Michael Buro

DOI10.1007/3-540-48957-6_8

Source URL

Citations81

SJR quartileQ2

SJR score0.35

SNIP0.55

TL;DR

A practical framework for the semi-automatic construction of evaluation-functions for games based on a structured evaluation function representation is presented that is able to discover new features in a computationally feasible way.

Abstract

This paper discusses a practical framework for the semi-automatic construction of evaluation-functions for games. Based on a structured evaluation function representation, a procedure for exploring the feature space is presented that is able to discover new features in a computationally feasible way. Besides the theoretical aspects, related practical issues such as the generation of training positions, feature selection, and weight fitting in large linear systems are discussed. Finally, we present experimental results for Othello, which demonstrate the potential of the described approach.

Keywords

Computer ScienceEconomics, Econometrics and Finance

IBM Journal of Research and DevelopmentSome Studies in Machine Learning Using the Game of Checkers

4,355 Citations1959Arthur L. Samuel

A new signature-table technique is described together with an improved book-learning procedure which is thought to be much superior to the linear polynomial method and to permit the program to look ahead to a much greater depth than it otherwise could do.

Communications of the ACMTemporal difference learning and TD-Gammon

1,485 Citations1995Gerald Tesauro

The domain of complex board games such as Go, chess, checkers, Othello, and backgammon has been widely regarded as an ideal testing ground for exploring a variety of concepts and approaches in artificial intelligence and machine learning.

View PDF

IBM Journal of Research and DevelopmentSome studies in machine learning using the game of checkers

1,418 Citations2000Arthur L. Samuel

Neural ComputationTD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play

800 Citations1994Gerald Tesauro

The latest version of TD-Gammon is now estimated to play at a strong master level that is extremely close to the world's best human players.

ICGA JournalTemporal Difference Learning and TD-Gammon

763 Citations1995G. Tesauro

View PDF

ICGA JournalThe Othello Match of the Year: Takeshi Murakami vs. Logistello

65 Citations1997Michael Buro

This report summarizes the first multi-game match between an Othello World Champion and a strong program named LOGISTELLO, which concluded that the best Othella programs have become stronger than any human player.

Meiosis Networks

62 Citations1989Stephen José Hanson

It is shown in a number of benchmark problems that meiosis networks can find minimal architectures, reduce computational complexity, and overall increase the efficiency of the representation learning interaction.

Neural Computing and ApplicationsNode splitting: A constructive algorithm for feed-forward neural networks

57 Citations1993Mike Wynne-Jones

A constructive algorithm is proposed for feed-forward neural networks which uses node-splitting in the hidden layers to build large networks from smaller ones.

Elsevier eBooksAdaptive Pattern-Oriented Chess

50 Citations1991Robert Levinson, Richard C. Snyder

The main objectives of the project are to demonstrate capacity of the system to learn, to deepen the understanding of the interaction of knowledge and search, and to build bridges in this area between AI and cognitive science.

Constructive Function Approximation

38 Citations1998Paul E. Utgoff, Doina Precup

Three algorithms are applied to two tasks, measuring the error in the approximated function as learning proceeds, and issues of feature overlap, independence, and coverage are addressed.