GP-RARS: Evolving controllers for the Robot Auto Racing Simulator

Yehonatan Shichel; Moshe Sipper

doi:10.1007/s12293-011-0056-9

GP-RARS: Evolving controllers for the Robot Auto Racing Simulator

Yehonatan Shichel
, Moshe Sipper

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

5 Scopus citations

Abstract

We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator). Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of game tracks.

Original language	English
Pages (from-to)	89-99
Number of pages	11
Journal	Memetic Computing
Volume	3
Issue number	2
DOIs	https://doi.org/10.1007/s12293-011-0056-9
State	Published - 1 Jul 2011

Keywords

Games
Genetic programming
RARS

ASJC Scopus subject areas

General Computer Science
Control and Optimization

Access to Document

10.1007/s12293-011-0056-9

Cite this

@article{384eb66148c24b97ad1b98a3c442f32f,

title = "GP-RARS: Evolving controllers for the Robot Auto Racing Simulator",

abstract = "We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator). Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of game tracks.",

keywords = "Games, Genetic programming, RARS",

author = "Yehonatan Shichel and Moshe Sipper",

year = "2011",

month = jul,

day = "1",

doi = "10.1007/s12293-011-0056-9",

language = "English",

volume = "3",

pages = "89--99",

journal = "Memetic Computing",

issn = "1865-9284",

publisher = "Springer Verlag",

number = "2",

}

TY - JOUR

T1 - GP-RARS

T2 - Evolving controllers for the Robot Auto Racing Simulator

AU - Shichel, Yehonatan

AU - Sipper, Moshe

PY - 2011/7/1

Y1 - 2011/7/1

N2 - We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator). Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of game tracks.

AB - We use evolutionary computation techniques to create real-time reactive controllers for a race-car simulation game: RARS (Robot Auto Racing Simulator). Using genetic programming to evolve driver controllers, we create highly generalized game-playing agents, able to outperform most human-crafted controllers and all machine-designed ones on a variety of game tracks.

KW - Games

KW - Genetic programming

KW - RARS

UR - https://www.scopus.com/pages/publications/79959378564

U2 - 10.1007/s12293-011-0056-9

DO - 10.1007/s12293-011-0056-9

M3 - Article

AN - SCOPUS:79959378564

SN - 1865-9284

VL - 3

SP - 89

EP - 99

JO - Memetic Computing

JF - Memetic Computing

IS - 2

ER -

GP-RARS: Evolving controllers for the Robot Auto Racing Simulator

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this