Year: 2007
Type: article
Abstract: In this paper we present a general, flexible framework for learning mappings from images to actions by interacting with the environment. The basic idea is to introduce a feature-based image classifier in front of a reinforcement learning algorithm. The classifier partitions the visual space according to the presence or absence of few highly informative local descriptors that are incrementally selected in a sequence of attempts to remove perceptual aliasing. We also address the problem of fighting overfitting in such a greedy algorithm. Finally, we show how high-level visual features can be generated when the power of local descriptors is insufficient for completely disambiguating the aliased states. This is done by building a hierarchy of composite features that consist of recursive spatial combinations of visual features. We demonstrate the efficacy of our algorithms by solving three visual navigation tasks and a visual version of the classical ``Car on the Hill'' control problem.
DOI: 10.1613/jair.2110
Authors: S. R. Jodogne, J. H. Piater
Institution: University of Liège
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W2117494236