Learning what to ignore: Memetic climbing in topology and weight space

Julian Togelius, Faustino Gomez, Jürgen Schmidhuber

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

    Abstract

    We present the memetic climber, a simple search algorithm that learns topology and weights of neural networks on different time scales. When applied to the problem of learning control for a simulated racing task with carefully selected inputs to the neural network, the memetie climber outperforms a standard hill-climber. When inputs to the network are less carefully selected, the difference is drastic. We also present two variations of the memetie climber and discuss the generalization of the underlying principle to population-based neuroevolution algorithms.

    Original languageEnglish (US)
    Title of host publication2008 IEEE Congress on Evolutionary Computation, CEC 2008
    Pages3274-3281
    Number of pages8
    DOIs
    Publication statusPublished - 2008
    Event2008 IEEE Congress on Evolutionary Computation, CEC 2008 - Hong Kong, China
    Duration: Jun 1 2008Jun 6 2008

    Other

    Other2008 IEEE Congress on Evolutionary Computation, CEC 2008
    CountryChina
    CityHong Kong
    Period6/1/086/6/08

      Fingerprint

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Theoretical Computer Science

    Cite this

    Togelius, J., Gomez, F., & Schmidhuber, J. (2008). Learning what to ignore: Memetic climbing in topology and weight space. In 2008 IEEE Congress on Evolutionary Computation, CEC 2008 (pp. 3274-3281). [4631241] https://doi.org/10.1109/CEC.2008.4631241