Interactive Selection of Visual Features through Reinforcement Learning

We introduce a new class of Reinforcement Learning algorithms designed to operate in perceptual spaces containing images. They work by classifying the percepts using a computer vision algorithm specialized in image recognition, hence reducing the visual percepts to a symbolic class. This approach ha...

Full description

Saved in:
Bibliographic Details
Published inResearch and Development in Intelligent Systems XXI pp. 285 - 298
Main Authors Jodogne, Sébastien, Piater, Justus H.
Format Book Chapter
LanguageEnglish
Published London Springer London
Subjects
Binary Number
Interest Point
Optimal Policy
Reinforcement Learn
Visual Feature
Online AccessGet full text

Cover

More Information
Summary:We introduce a new class of Reinforcement Learning algorithms designed to operate in perceptual spaces containing images. They work by classifying the percepts using a computer vision algorithm specialized in image recognition, hence reducing the visual percepts to a symbolic class. This approach has the advantage of overcoming to some extent the curse of dimensionality by focusing the attention of the agent on distinctive and robust visual features. The visual classes are learned automatically in a process that only relies on the reinforcement earned by the agent during its interaction with the environment. In this sense, the visual classes are learned interactively in a task-driven fashion, without an external supervisor. We also show how our algorithms can be extended to perceptual spaces, large or even continuous, upon which it is possible to define features.
Bibliography:Research Fellow of the Belgian National Fund for Scientific Research (FNRS).
ISBN:1852339071
9781852339074
DOI:10.1007/1-84628-102-4_21