@InProceedings{Supelec915,
author = {Bilal PIOT and Matthieu Geist and Olivier Pietquin},
title = {{Imitation Learning Applied to Embodied Conversational Agents}},
year = {2015},
booktitle = {{Machine Learning and Interactive Systems (MLIS)}},
url = {http://www.metz.supelec.fr//metz/personnel/geist_mat/pdfs/mlis_15.pdf},
abstract = {Embodied Conversational Agents (ECAs) are emerging as a key
component to allow human interact with machines. Applications are
numerous and ECAs
can reduce the aversion to interact with a machine by providing
user-friendly interfaces. Yet, ECAs are still unable to produce
social signals appropriately during their interaction with humans,
which tends to make the interaction less instinctive. Especially,
very little attention has been paid to the use of laughter in
human-avatar interactions despite the crucial role played by laughter
in human-human interaction. In this paper, methods for predicting
when and how to laugh during an interaction for an ECA are proposed.
Different Imitation Learning (also known as Apprenticeship
Learning) algorithms are used in this purpose and a regularized
classification algorithm is shown to produce good behavior on
real data.}
}