publication . Conference object . 2017

autoencoder augmented neuroevolution for visual doom playing

Samuel Alvernaz; Julian Togelius;
Open Access
  • Published: 31 Oct 2017
  • Publisher: IEEE
Abstract
Neuroevolution has proven effective at many re-inforcement learning tasks, including tasks with incomplete information and delayed rewards, but does not seem to scale well to high-dimensional controller representations, which are needed for tasks where the input is raw pixel data. We propose a novel method where we train an autoencoder to create a comparatively low-dimensional representation of the environment observation, and then use CMA-ES to train neural network controllers acting on this input data. As the behavior of the agent changes the nature of the input data, the autoencoder training progresses throughout evolution. We test this method in the VizDoom ...
Subjects
free text keywords: Control theory, Autoencoder, Visualization, Complete information, Evolutionary computation, Machine learning, computer.software_genre, computer, Artificial neural network, Neuroevolution, Computer science, Artificial intelligence, business.industry, business, Pixel
Related Organizations
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue