Back to Search
Start Over
Deep Learning and Hierarchical Reinforcement Learning for modeling a Conversational Recommender System.
- Source :
-
Intelligenza Artificiale . 2018, Vol. 12 Issue 2, p125-141. 17p. - Publication Year :
- 2018
-
Abstract
- In this paper, we propose a framework based on Hierarchical Reinforcement Learning for dialogue management in a Conversational Recommender System scenario. The framework splits the dialogue into more manageable tasks whose achievement corresponds to goals of the dialogue with the user. The framework consists of a meta-controller, which receives the user utterance and understands which goal should pursue, and a controller, which exploits a goal-specific representation to generate an answer composed by a sequence of tokens. The modules are trained using a two-stage strategy based on a preliminary Supervised Learning stage and a successive Reinforcement Learning stage. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 17248035
- Volume :
- 12
- Issue :
- 2
- Database :
- Academic Search Index
- Journal :
- Intelligenza Artificiale
- Publication Type :
- Academic Journal
- Accession number :
- 134378892
- Full Text :
- https://doi.org/10.3233/IA-170031