Evolving Artificial General Intelligence for Video Game Controllers.

Itay Azaria; Achiya Elyasaf; Moshe Sipper

doi:10.1007/978-3-319-97088-2_4

Evolving Artificial General Intelligence for Video Game Controllers.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The General Video Game Playing Competition (GVGAI) defines a challenge of creating controllers for general video game playing, a testbed—as it were—for examining the issue of artificial general intelligence. We develop herein a game controller that mimics human learning behavior, focusing on the ability to generalize from experience and diminish learning time as new games present themselves. We use genetic programming to evolve hyper-heuristic-based general players. Our results show the effectiveness of evolution in meeting the generality challenge.

Original language	English
Title of host publication	Genetic Programming Theory and Practice XIV
Editors	R. Riolo, B. Worzel, B. Goldman , B. Tozier
Publisher	Springer
Pages	53-63
ISBN (Electronic)	978-3-319-97088-2
ISBN (Print)	978-3-319-97087-5
DOIs	https://doi.org/10.1007/978-3-319-97088-2_4
State	Published - 28 Oct 2018

Keywords

Genetic programming
Hyper-heuristics
Video games
GVG-AI competition

Access to Document

10.1007/978-3-319-97088-2_4

https://dblp.org/db/conf/gptp/gptp2016.html#AzariaES16

Cite this

@inproceedings{fdd0a098104a4f059f35030a0b40c2e0,

title = "Evolving Artificial General Intelligence for Video Game Controllers.",

abstract = "The General Video Game Playing Competition (GVGAI) defines a challenge of creating controllers for general video game playing, a testbed—as it were—for examining the issue of artificial general intelligence. We develop herein a game controller that mimics human learning behavior, focusing on the ability to generalize from experience and diminish learning time as new games present themselves. We use genetic programming to evolve hyper-heuristic-based general players. Our results show the effectiveness of evolution in meeting the generality challenge.",

keywords = "Genetic programming, Hyper-heuristics, Video games, GVG-AI competition",

author = "Itay Azaria and Achiya Elyasaf and Moshe Sipper",

note = "DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.",

year = "2018",

month = oct,

day = "28",

doi = "10.1007/978-3-319-97088-2\_4",

language = "English",

isbn = "978-3-319-97087-5",

pages = "53--63",

editor = "R. Riolo and B. Worzel and \{Goldman \}, B. and B. Tozier",

booktitle = "Genetic Programming Theory and Practice XIV",

publisher = "Springer",

address = "Germany",

}

TY - GEN

T1 - Evolving Artificial General Intelligence for Video Game Controllers.

AU - Azaria, Itay

AU - Elyasaf, Achiya

AU - Sipper, Moshe

N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.

PY - 2018/10/28

Y1 - 2018/10/28

N2 - The General Video Game Playing Competition (GVGAI) defines a challenge of creating controllers for general video game playing, a testbed—as it were—for examining the issue of artificial general intelligence. We develop herein a game controller that mimics human learning behavior, focusing on the ability to generalize from experience and diminish learning time as new games present themselves. We use genetic programming to evolve hyper-heuristic-based general players. Our results show the effectiveness of evolution in meeting the generality challenge.

AB - The General Video Game Playing Competition (GVGAI) defines a challenge of creating controllers for general video game playing, a testbed—as it were—for examining the issue of artificial general intelligence. We develop herein a game controller that mimics human learning behavior, focusing on the ability to generalize from experience and diminish learning time as new games present themselves. We use genetic programming to evolve hyper-heuristic-based general players. Our results show the effectiveness of evolution in meeting the generality challenge.

KW - Genetic programming

KW - Hyper-heuristics

KW - Video games

KW - GVG-AI competition

U2 - 10.1007/978-3-319-97088-2_4

DO - 10.1007/978-3-319-97088-2_4

M3 - Conference contribution

SN - 978-3-319-97087-5

SP - 53

EP - 63

BT - Genetic Programming Theory and Practice XIV

A2 - Riolo, R.

A2 - Worzel, B.

A2 - Goldman , B.

A2 - Tozier, B.

PB - Springer

ER -

Evolving Artificial General Intelligence for Video Game Controllers.

Abstract

Keywords

Access to Document

Fingerprint

Cite this