Designing an evolutionary strategizing machine for game playing and beyond

Moshe Sipper; Yaniv Azaria; Ami Hauptman; Yehonatan Shichel

doi:10.1109/TSMCC.2007.897326

Designing an evolutionary strategizing machine for game playing and beyond

Moshe Sipper, Yaniv Azaria, Ami Hauptman, Yehonatan Shichel

Department of Computer Science

Research output: Contribution to journal › Article › peer-review

30 Scopus citations

Abstract

We have recently shown that genetically programming game players, after having imbued the evolutionary process with human intelligence, produces human-competitive strategies for three games: backgammon, chess endgames, and robocode (tank-fight simulation). Evolved game players are able to hold their own-and often win-against human or human-based competitors. This paper has a twofold objective: first, to review our recent results of applying genetic programming in the domain of games; second, to formulate the merits of genetic programming in acting as a tool for developing strategies in general, and to discuss the possible design of a strategizing machine.

Original language	English
Pages (from-to)	583-593
Number of pages	11
Journal	IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews
Volume	37
Issue number	4
DOIs	https://doi.org/10.1109/TSMCC.2007.897326
State	Published - 1 Jul 2007

Keywords

Backgammon
Chess
Evolutionary algorithms
Evolving game strategies
Genetic programming
Robocode
Strategizing

ASJC Scopus subject areas

Control and Systems Engineering
Software
Information Systems
Human-Computer Interaction
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TSMCC.2007.897326

Cite this

@article{e5cb8c541b7d40c892c71488b972f2dc,

title = "Designing an evolutionary strategizing machine for game playing and beyond",

abstract = "We have recently shown that genetically programming game players, after having imbued the evolutionary process with human intelligence, produces human-competitive strategies for three games: backgammon, chess endgames, and robocode (tank-fight simulation). Evolved game players are able to hold their own-and often win-against human or human-based competitors. This paper has a twofold objective: first, to review our recent results of applying genetic programming in the domain of games; second, to formulate the merits of genetic programming in acting as a tool for developing strategies in general, and to discuss the possible design of a strategizing machine.",

keywords = "Backgammon, Chess, Evolutionary algorithms, Evolving game strategies, Genetic programming, Robocode, Strategizing",

author = "Moshe Sipper and Yaniv Azaria and Ami Hauptman and Yehonatan Shichel",

year = "2007",

month = jul,

day = "1",

doi = "10.1109/TSMCC.2007.897326",

language = "English",

volume = "37",

pages = "583--593",

journal = "IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews",

issn = "1094-6977",

publisher = "Institute of Electrical and Electronics Engineers",

number = "4",

}

TY - JOUR

T1 - Designing an evolutionary strategizing machine for game playing and beyond

AU - Sipper, Moshe

AU - Azaria, Yaniv

AU - Hauptman, Ami

AU - Shichel, Yehonatan

PY - 2007/7/1

Y1 - 2007/7/1

N2 - We have recently shown that genetically programming game players, after having imbued the evolutionary process with human intelligence, produces human-competitive strategies for three games: backgammon, chess endgames, and robocode (tank-fight simulation). Evolved game players are able to hold their own-and often win-against human or human-based competitors. This paper has a twofold objective: first, to review our recent results of applying genetic programming in the domain of games; second, to formulate the merits of genetic programming in acting as a tool for developing strategies in general, and to discuss the possible design of a strategizing machine.

AB - We have recently shown that genetically programming game players, after having imbued the evolutionary process with human intelligence, produces human-competitive strategies for three games: backgammon, chess endgames, and robocode (tank-fight simulation). Evolved game players are able to hold their own-and often win-against human or human-based competitors. This paper has a twofold objective: first, to review our recent results of applying genetic programming in the domain of games; second, to formulate the merits of genetic programming in acting as a tool for developing strategies in general, and to discuss the possible design of a strategizing machine.

KW - Backgammon

KW - Chess

KW - Evolutionary algorithms

KW - Evolving game strategies

KW - Genetic programming

KW - Robocode

KW - Strategizing

UR - http://www.scopus.com/inward/record.url?scp=34447331426&partnerID=8YFLogxK

U2 - 10.1109/TSMCC.2007.897326

DO - 10.1109/TSMCC.2007.897326

M3 - Article

AN - SCOPUS:34447331426

SN - 1094-6977

VL - 37

SP - 583

EP - 593

JO - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

JF - IEEE Transactions on Systems, Man and Cybernetics Part C: Applications and Reviews

IS - 4

ER -

Designing an evolutionary strategizing machine for game playing and beyond

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this