Social signal and user adaptation in reinforcement learning-based dialogue management - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

Social signal and user adaptation in reinforcement learning-based dialogue management

Emmanuel Ferreira
  • Fonction : Auteur
  • PersonId : 982139
Fabrice Lefèvre

Résumé

This paper investigates the conditions under which cues from social signals can be used for user adaptation (or user tracking) of a learning agent. In this work we consider the case of the Reinforcement Learning (RL) of a dialogue management module. Social signals (gazes, postures, emotions, etc.) have an undeniable importance in human interactions and can be used as an additional and user-dependent (subjective) reinforcement signal during learning. In this paper, the Kalman Temporal Differences (KTD) framework is employed in combination with a potential-based shaping reward method to properly integrate the social information in the optimisa-tion procedure and adapt the policy to user profiles. In a second step the ability of the method to track a new user profile (after self learning of the user or switch to a new user) is shown. Experiments carried out using a state-of-the-art goal-oriented dialogue management framework with simulations support our claims.
Fichier non déposé

Dates et versions

hal-01315527 , version 1 (13-05-2016)

Identifiants

Citer

Emmanuel Ferreira, Fabrice Lefèvre. Social signal and user adaptation in reinforcement learning-based dialogue management. MLIS '13 Proceedings of the 2nd Workshop on Machine Learning for Interactive Systems: Bridging the Gap Between Perception, Action and Communication , Aug 2013, Beijing, China. ⟨10.1145/2493525.2493535⟩. ⟨hal-01315527⟩

Collections

UNIV-AVIGNON LIA
72 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More