Skip to yearly menu bar Skip to main content


Demonstration

A Deep Reinforcement Learning Chatbot

Iulian Vlad Serban · Chinnadhurai Sankar · Mathieu Germain · Saizheng Zhang · Zhouhan Lin · Sandeep Subramanian · Taesup Kim · Michael Pieper · Sarath Chandar · Nan Rosemary Ke · Sai Rajeswar Mudumba · Alexandre de BrĂ©bisson · Jose Sotelo · Dendi A Suhubdy · Vincent Michalski · Joelle Pineau · Yoshua Bengio

Pacific Ballroom Concourse # D1

Abstract:

Dialogue systems and conversational agents - including chatbots, personal assistants and voice-control interfaces - are becoming ubiquitous in modern society. Examples of these include personal assistants on mobile devices, customer service assistants and technical support help, as well as online bots selling anything from fashion clothes, cosmetics to legal advice and self-help therapy. However, building high-quality intelligent conversational agents remains a major challenge for artificial intelligence.

This paper summarizes the chatbot system developed by the team at the Montreal Institute of Learning Algorithms, which also participated in the Amazon Alexa Prize competition held between 2016 - 2017.1 The system is a social bot: a spoken conversation alagent capable of conversing engagingly with humans on popular topics. Between April and August, 2017, the system has had over ten thousand conversations with real-world users in the Amazon Alexa Prize competition.

Live content is unavailable. Log in and register to view live content