Exploration and Exploitation in Visuomotor Prediction of Autonomous Agents
Machine Learning
2013-10-01 v1 Computer Vision and Pattern Recognition
Dynamical Systems
Abstract
This paper discusses various techniques to let an agent learn how to predict the effects of its own actions on its sensor data autonomously, and their usefulness to apply them to visual sensors. An Extreme Learning Machine is used for visuomotor prediction, while various autonomous control techniques that can aid the prediction process by balancing exploration and exploitation are discussed and tested in a simple system: a camera moving over a 2D greyscale image.
Keywords
Cite
@article{arxiv.1309.7959,
title = {Exploration and Exploitation in Visuomotor Prediction of Autonomous Agents},
author = {Laurens Bliek},
journal= {arXiv preprint arXiv:1309.7959},
year = {2013}
}
Comments
Award-winning paper of the internal conference 'Almende research workshop 2013'