Evolving robust and specialized car racing skills

Julian Togelius, Simon M. Lucas

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able tn perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It Is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.

    Original languageEnglish (US)
    Title of host publication2006 IEEE Congress on Evolutionary Computation, CEC 2006
    Pages1187-1194
    Number of pages8
    StatePublished - 2006
    Event2006 IEEE Congress on Evolutionary Computation, CEC 2006 - Vancouver, BC, Canada
    Duration: Jul 16 2006Jul 21 2006

    Other

    Other2006 IEEE Congress on Evolutionary Computation, CEC 2006
    CountryCanada
    CityVancouver, BC
    Period7/16/067/21/06

    Fingerprint

    Railroad cars
    Controller
    Controllers
    Evolutionary Robotics
    Computer games
    Railroad tracks
    Computer Games
    Testbeds
    Testbed
    Fitness
    Robotics
    Skills
    Neural Networks
    Neural networks
    Sensor
    Sensors

    Keywords

    • Driving
    • Ear racing
    • Evolutionary robotics
    • Games
    • Incremental evolution

    ASJC Scopus subject areas

    • Artificial Intelligence
    • Software
    • Theoretical Computer Science

    Cite this

    Togelius, J., & Lucas, S. M. (2006). Evolving robust and specialized car racing skills. In 2006 IEEE Congress on Evolutionary Computation, CEC 2006 (pp. 1187-1194). [1688444]

    Evolving robust and specialized car racing skills. / Togelius, Julian; Lucas, Simon M.

    2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1187-1194 1688444.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Togelius, J & Lucas, SM 2006, Evolving robust and specialized car racing skills. in 2006 IEEE Congress on Evolutionary Computation, CEC 2006., 1688444, pp. 1187-1194, 2006 IEEE Congress on Evolutionary Computation, CEC 2006, Vancouver, BC, Canada, 7/16/06.
    Togelius J, Lucas SM. Evolving robust and specialized car racing skills. In 2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. p. 1187-1194. 1688444
    Togelius, Julian ; Lucas, Simon M. / Evolving robust and specialized car racing skills. 2006 IEEE Congress on Evolutionary Computation, CEC 2006. 2006. pp. 1187-1194
    @inproceedings{ff1e58b466c24a4c8017c71288cc96e4,
    title = "Evolving robust and specialized car racing skills",
    abstract = "Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able tn perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It Is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.",
    keywords = "Driving, Ear racing, Evolutionary robotics, Games, Incremental evolution",
    author = "Julian Togelius and Lucas, {Simon M.}",
    year = "2006",
    language = "English (US)",
    isbn = "0780394879",
    pages = "1187--1194",
    booktitle = "2006 IEEE Congress on Evolutionary Computation, CEC 2006",

    }

    TY - GEN

    T1 - Evolving robust and specialized car racing skills

    AU - Togelius, Julian

    AU - Lucas, Simon M.

    PY - 2006

    Y1 - 2006

    N2 - Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able tn perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It Is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.

    AB - Neural network-based controllers are evolved for racing simulated R/C cars around several tracks of varying difficulty. The transferability of driving skills acquired when evolving for a single track is evaluated, and different ways of evolving controllers able tn perform well on many different tracks are investigated. It is further shown that such generally proficient controllers can reliably be developed into specialized controllers for individual tracks. Evolution of sensor parameters together with network weights is shown to lead to higher final fitness, but only if turned on after a general controller is developed, otherwise it hinders evolution. It Is argued that simulated car racing is a scalable and relevant testbed for evolutionary robotics research, and that the results of this research can be useful for commercial computer games.

    KW - Driving

    KW - Ear racing

    KW - Evolutionary robotics

    KW - Games

    KW - Incremental evolution

    UR - http://www.scopus.com/inward/record.url?scp=34547257008&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=34547257008&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:34547257008

    SN - 0780394879

    SN - 9780780394872

    SP - 1187

    EP - 1194

    BT - 2006 IEEE Congress on Evolutionary Computation, CEC 2006

    ER -