Knowledge of Knowledge and Intelligent Experimentation for Learning Control - Robotics Institute Carnegie Mellon University

Knowledge of Knowledge and Intelligent Experimentation for Learning Control

Andrew Moore
Conference Paper, Proceedings of Seattle International Joint Conference on Neural Networks, Vol. 2, pp. 683 - 688, July, 1991

Abstract

It is shown that if a learning system is able to provide some estimate of the reliability of the generalizations it produces, then the rate of learning can be considerably increased. The increase is achieved by a decision-theoretic estimate of the value of trying alternative experimental actions. A further consequence of this kind of learning is that experience becomes concentrated in regions of the control space which are relevant to the task at hand. Such a restriction of experience is essential for continuous multivariate control tasks because the entire state space of such tasks could not possibly be learned in a practical amount of time.

BibTeX

@conference{Moore-1991-13275,
author = {Andrew Moore},
title = {Knowledge of Knowledge and Intelligent Experimentation for Learning Control},
booktitle = {Proceedings of Seattle International Joint Conference on Neural Networks},
year = {1991},
month = {July},
volume = {2},
pages = {683 - 688},
}