SimpleDS: A Simple Deep Reinforcement Learning Dialogue System

Abstract

This paper presents 'SimpleDS', a simple and publicly available dialogue system trained with deep reinforcement learning. In contrast to previous reinforcement learning dialogue systems, this system avoids manual feature engineering by performing action selection directly from raw text of the last system and (noisy) user responses. Our initial results, in the restaurant domain, show that it is indeed possible to induce reasonable dialogue behaviour with an approach that aims for high levels of automation in dialogue control for intelligent interactive agents.

International Workshop on Spoken Dialogue Systems (IWSDS), 2016

References in corpus (1)

• Playing Atari with Deep Reinforcement Learning

Cited by in corpus (6)

• Towards End-to-End Reinforcement Learning of Dialogue Agents for Information Access
• Learning Robust Dialog Policies in Noisy Environments
• Towards Personalized Dialog Policies for Conversational Skill Discovery
• DRL: Deep Reinforcement Learning for Intelligent Robot Control -- Concept, Literature, and Future
• Training an Interactive Humanoid Robot Using Multimodal Deep Reinforcement Learning
• Integrating User and Agent Models: A Deep Task-Oriented Dialogue System