Evolving controllers for simulated car racing

Simple item page
dc.creatorTogelius, Julian
dc.creatorLucas, Simon M.
dc.date2006-11-02
dc.date.accessioned2026-07-07T07:31:38Z
dc.date.available2026-07-07T07:31:38Z
dc.descriptionThis paper describes the evolution of controllers for racing a simulated radio-controlled car around a track, modelled on a real physical track. Five different controller architectures were compared, based on neural networks, force fields and action sequences. The controllers use either egocentric (first person), Newtonian (third person) or no information about the state of the car (open-loop controller). The only controller that was able to evolve good racing behaviour was based on a neural network acting on egocentric inputs.
dc.descriptionWon the CEC 2005 Best Student Paper Award
dc.identifierhttps://arxiv.org/abs/cs/0611006
dc.identifierhttp://arxiv.org/abs/cs/0611006
dc.identifierProceedings of the 2005 Congress on Evolutionary Computation, pages 1906-1913
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/118824
dc.subjectNeural and Evolutionary Computing
dc.subjectMachine Learning
dc.subjectRobotics
dc.titleEvolving controllers for simulated car racing
dc.typetext

Files

Collections

arXiv