Evolving controllers for simulated car racing using object oriented genetic programming

Alexandros Agapitos; Julian Togelius; Simon Mark Lucas

doi:10.1145/1276958.1277271

Evolving controllers for simulated car racing using object oriented genetic programming

Alexandros Agapitos, Julian Togelius, Simon Mark Lucas

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

Abstract

Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed.

Original language	English (US)
Title of host publication	Proceedings of GECCO 2007
Subtitle of host publication	Genetic and Evolutionary Computation Conference
Pages	1543-1550
Number of pages	8
DOIs	https://doi.org/10.1145/1276958.1277271
State	Published - 2007
Event	9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007 - London, United Kingdom Duration: Jul 7 2007 → Jul 11 2007

Publication series

Name	Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

Other

Other	9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007
Country/Territory	United Kingdom
City	London
Period	7/7/07 → 7/11/07

Keywords

Evolutionary computer games
Evolutionary robotics
Genetic programming
Homologous uniform crossover
Neural networks
Object-oriented
Subtree macro-mutation

ASJC Scopus subject areas

Artificial Intelligence
Software
Theoretical Computer Science

Access to Document

10.1145/1276958.1277271

Cite this

Evolving controllers for simulated car racing using object oriented genetic programming. / Agapitos, Alexandros; Togelius, Julian; Lucas, Simon Mark.
Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. 2007. p. 1543-1550 (Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference).

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

Agapitos, A, Togelius, J & Lucas, SM 2007, Evolving controllers for simulated car racing using object oriented genetic programming. in Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference. Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference, pp. 1543-1550, 9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007, London, United Kingdom, 7/7/07. https://doi.org/10.1145/1276958.1277271

@inproceedings{f9cb1008d3e3485886263bfe90e80a66,

title = "Evolving controllers for simulated car racing using object oriented genetic programming",

abstract = "Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed.",

keywords = "Evolutionary computer games, Evolutionary robotics, Genetic programming, Homologous uniform crossover, Neural networks, Object-oriented, Subtree macro-mutation",

author = "Alexandros Agapitos and Julian Togelius and Lucas, {Simon Mark}",

year = "2007",

doi = "10.1145/1276958.1277271",

language = "English (US)",

isbn = "1595936971",

series = "Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference",

pages = "1543--1550",

booktitle = "Proceedings of GECCO 2007",

note = "9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007 ; Conference date: 07-07-2007 Through 11-07-2007",

}

TY - GEN

T1 - Evolving controllers for simulated car racing using object oriented genetic programming

AU - Agapitos, Alexandros

AU - Togelius, Julian

AU - Lucas, Simon Mark

PY - 2007

Y1 - 2007

N2 - Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed.

AB - Several different controller representations are compared on anon-trivial problem in simulated car racing, with respect tolearning speed and final fitness. The controller representations arebased either on Neural Networks or Genetic Programming, and alsodiffer in regards to whether they allow for stateful controllers orjust reactive ones. Evolved GP trees are analysed, and attempts aremade at explaining the performance differences observed.

KW - Evolutionary computer games

KW - Evolutionary robotics

KW - Genetic programming

KW - Homologous uniform crossover

KW - Neural networks

KW - Object-oriented

KW - Subtree macro-mutation

UR - http://www.scopus.com/inward/record.url?scp=34548062086&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548062086&partnerID=8YFLogxK

U2 - 10.1145/1276958.1277271

DO - 10.1145/1276958.1277271

M3 - Conference contribution

AN - SCOPUS:34548062086

SN - 1595936971

SN - 9781595936974

T3 - Proceedings of GECCO 2007: Genetic and Evolutionary Computation Conference

SP - 1543

EP - 1550

BT - Proceedings of GECCO 2007

T2 - 9th Annual Genetic and Evolutionary Computation Conference, GECCO 2007

Y2 - 7 July 2007 through 11 July 2007

ER -

Evolving controllers for simulated car racing using object oriented genetic programming

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this