Multiobjective techniques for the use of state in genetic programming applied to simulated car racing

Alexandras Agapitos; Julian Togelius; Simon M. Lucas

doi:10.1109/CEC.2007.4424659

Multiobjective techniques for the use of state in genetic programming applied to simulated car racing

Alexandras Agapitos, Julian Togelius, Simon M. Lucas

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

Abstract

Multi-objective optimisation is applied to encourage the effective use of state variables in car controlling programs evolved using Genetic Programming. Three different metrics for measuring the use of state within a program are introduced. Comparisons are performed among multi- and single-objective fitness functions with respect to learning speed and final fitness of evolved individuals, and attempts are made at understanding whether there is a trade-off between good performance and stateful controllers in this problem domain.

Original language	English (US)
Title of host publication	2007 IEEE Congress on Evolutionary Computation, CEC 2007
Pages	1562-1569
Number of pages	8
DOIs	https://doi.org/10.1109/CEC.2007.4424659
State	Published - 2007
Event	2007 IEEE Congress on Evolutionary Computation, CEC 2007 - , Singapore Duration: Sep 25 2007 → Sep 28 2007

Publication series

Name	2007 IEEE Congress on Evolutionary Computation, CEC 2007

Other

Other	2007 IEEE Congress on Evolutionary Computation, CEC 2007
Country	Singapore
Period	9/25/07 → 9/28/07

ASJC Scopus subject areas

Artificial Intelligence
Software
Theoretical Computer Science

Access to Document

10.1109/CEC.2007.4424659

Fingerprint Dive into the research topics of 'Multiobjective techniques for the use of state in genetic programming applied to simulated car racing'. Together they form a unique fingerprint.

Cite this

Multiobjective techniques for the use of state in genetic programming applied to simulated car racing. / Agapitos, Alexandras; Togelius, Julian; Lucas, Simon M.

2007 IEEE Congress on Evolutionary Computation, CEC 2007. 2007. p. 1562-1569 4424659 (2007 IEEE Congress on Evolutionary Computation, CEC 2007).

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

Agapitos, A, Togelius, J & Lucas, SM 2007, Multiobjective techniques for the use of state in genetic programming applied to simulated car racing. in 2007 IEEE Congress on Evolutionary Computation, CEC 2007., 4424659, 2007 IEEE Congress on Evolutionary Computation, CEC 2007, pp. 1562-1569, 2007 IEEE Congress on Evolutionary Computation, CEC 2007, Singapore, 9/25/07. https://doi.org/10.1109/CEC.2007.4424659

@inproceedings{ad8d77f2aeaa4397a2bfbe7c58733483,

title = "Multiobjective techniques for the use of state in genetic programming applied to simulated car racing",

abstract = "Multi-objective optimisation is applied to encourage the effective use of state variables in car controlling programs evolved using Genetic Programming. Three different metrics for measuring the use of state within a program are introduced. Comparisons are performed among multi- and single-objective fitness functions with respect to learning speed and final fitness of evolved individuals, and attempts are made at understanding whether there is a trade-off between good performance and stateful controllers in this problem domain.",

author = "Alexandras Agapitos and Julian Togelius and Lucas, {Simon M.}",

year = "2007",

doi = "10.1109/CEC.2007.4424659",

language = "English (US)",

isbn = "1424413400",

series = "2007 IEEE Congress on Evolutionary Computation, CEC 2007",

pages = "1562--1569",

booktitle = "2007 IEEE Congress on Evolutionary Computation, CEC 2007",

note = "2007 IEEE Congress on Evolutionary Computation, CEC 2007 ; Conference date: 25-09-2007 Through 28-09-2007",

}

TY - GEN

T1 - Multiobjective techniques for the use of state in genetic programming applied to simulated car racing

AU - Agapitos, Alexandras

AU - Togelius, Julian

AU - Lucas, Simon M.

PY - 2007

Y1 - 2007

N2 - Multi-objective optimisation is applied to encourage the effective use of state variables in car controlling programs evolved using Genetic Programming. Three different metrics for measuring the use of state within a program are introduced. Comparisons are performed among multi- and single-objective fitness functions with respect to learning speed and final fitness of evolved individuals, and attempts are made at understanding whether there is a trade-off between good performance and stateful controllers in this problem domain.

AB - Multi-objective optimisation is applied to encourage the effective use of state variables in car controlling programs evolved using Genetic Programming. Three different metrics for measuring the use of state within a program are introduced. Comparisons are performed among multi- and single-objective fitness functions with respect to learning speed and final fitness of evolved individuals, and attempts are made at understanding whether there is a trade-off between good performance and stateful controllers in this problem domain.

UR - http://www.scopus.com/inward/record.url?scp=57349189257&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=57349189257&partnerID=8YFLogxK

U2 - 10.1109/CEC.2007.4424659

DO - 10.1109/CEC.2007.4424659

M3 - Conference contribution

AN - SCOPUS:57349189257

SN - 1424413400

SN - 9781424413409

T3 - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

SP - 1562

EP - 1569

BT - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

T2 - 2007 IEEE Congress on Evolutionary Computation, CEC 2007

Y2 - 25 September 2007 through 28 September 2007

ER -