A deep learning / neuroevolution hybrid for visual control

Andreas Precht Poulsen, Mark Thorhauge, Mikkel Hvilshj Funch, Sebastian Risi

    Publikation: Konference artikel i Proceeding eller bog/rapport kapitelKonferencebidrag i proceedingsForskningpeer review

    Abstract

    This paper presents a deep learning / neuroevolution hybrid approach called DLNE, which allows FPS bots to learn to aim & shoot based only on high-dimensional raw pixel input. The deep learning component is responsible for visual recognition and translating raw pixels to compact feature representations, while the evolving network takes those features as inputs to infer actions. The results suggest that combining deep learning and neuroevolution in a hybrid approach is a promising research direction that could make complex visual domains directly accessible to networks trained through evolution.
    OriginalsprogUdefineret/Ukendt
    TitelGECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
    Antal sider2
    ForlagAssociation for Computing Machinery
    Publikationsdato2017
    Sider93-94
    ISBN (Trykt)978-1-4503-4939-0
    DOI
    StatusUdgivet - 2017

    Emneord

    • Deep Learning
    • Neuroevolution
    • Hybrid Approach
    • FPS Bots
    • Visual Recognition

    Citationsformater