A deep learning / neuroevolution hybrid for visual control

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

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-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.
Original languageUndefined/Unknown
Title of host publicationGECCO '17 Proceedings of the Genetic and Evolutionary Computation Conference Companion
Number of pages2
PublisherAssociation for Computing Machinery
Publication date2017
Pages93-94
ISBN (Print)978-1-4503-4939-0
DOIs
Publication statusPublished - 2017

Keywords

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

Cite this