Imitation Learning Applied to Embodied Conversational Agents - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Imitation Learning Applied to Embodied Conversational Agents

Résumé

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.
Fichier principal
Vignette du fichier
piot15.pdf (400.43 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01225816 , version 1 (09-11-2015)

Identifiants

  • HAL Id : hal-01225816 , version 1

Citer

Bilal Piot, Matthieu Geist, Olivier Pietquin. Imitation Learning Applied to Embodied Conversational Agents. 4th Workshop on Machine Learning for Interactive Systems (MLIS 2015), Jul 2015, Lille, France. ⟨hal-01225816⟩
213 Consultations
79 Téléchargements

Partager

Gmail Facebook X LinkedIn More