Behavioral Cloning of Student Pilots with Modular Neural Networks
Abstract
This paper investigates how behavioral cloning can be used to decrease training time for students learning to fly on simulators. The challenges presented to each student must be tailored to their unique learning experiences. This requires an intelligent training regime that exploits a model of each student that predicts where the student's performance will be deficient. Here we show that cloning the behavior of student pilots with a modular neural network results in the automatic decomposition of the behavior into sets of skills. This decomposition may provide a means for identifying when certain skills are acquired by students and which skills are deficient. This information may then be used to decrease training time by altering the sequence of simulation experiences to just those that the student needs.
Cite
Text
Anderson et al. "Behavioral Cloning of Student Pilots with Modular Neural Networks." International Conference on Machine Learning, 2000.Markdown
[Anderson et al. "Behavioral Cloning of Student Pilots with Modular Neural Networks." International Conference on Machine Learning, 2000.](https://mlanthology.org/icml/2000/anderson2000icml-behavioral/)BibTeX
@inproceedings{anderson2000icml-behavioral,
title = {{Behavioral Cloning of Student Pilots with Modular Neural Networks}},
author = {Anderson, Charles W. and Draper, Bruce A. and Peterson, David A.},
booktitle = {International Conference on Machine Learning},
year = {2000},
pages = {25-32},
url = {https://mlanthology.org/icml/2000/anderson2000icml-behavioral/}
}