A Deep Reinforcement Learning Chatbot
Iulian Vlad Serban · Chinnadhurai Sankar · Mathieu Germain · Saizheng Zhang · Zhouhan Lin · Sandeep Subramanian · Taesup Kim · Michael Pieper · Sarath Chandar Anbil Parthipan · Nan Rosemary Ke · Sai Rajeswar Mudumba · Alexandre de Brébisson · Jose Sotelo · Dendi A Suhubdy · Vincent Michalski · Joelle Pineau · Yoshua Bengio

Tue Dec 5th 07:00 -- 10:30 PM @ Pacific Ballroom Concourse # D1
Event URL: »

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.

Author Information

Iulian Vlad Serban (MILA)
Chinnadhurai Sankar (MILA ( Montreal Institute of Learning Algorithms))
Mathieu Germain (MILA)
Saizheng Zhang (University of Montreal)
Zhouhan Lin (MILA)
Sandeep Subramanian (Université de Montréal)
Taesup Kim (Université de Montréal)
Mike Pieper (MILA)
Sarath Chandar Anbil Parthipan (Montreal Institute for Learning Algorithms)
Rosemary Ke (MILA, University of Montreal)
Sai Rajeswar Mudumba (University of Montreal)
Alexandre de Brébisson (Imperial College)
Jose Sotelo (Universite de Montreal)
Dendi A Suhubdy (MILA, Université de Montréal)
Vincent Michalski (Université de Montréal)
Joelle Pineau (McGill University)

Joelle Pineau is an Associate Professor and William Dawson Scholar at McGill University where she co-directs the Reasoning and Learning Lab. She also leads the Facebook AI Research lab in Montreal, Canada. She holds a BASc in Engineering from the University of Waterloo, and an MSc and PhD in Robotics from Carnegie Mellon University. Dr. Pineau's research focuses on developing new models and algorithms for planning and learning in complex partially-observable domains. She also works on applying these algorithms to complex problems in robotics, health care, games and conversational agents. She serves on the editorial board of the Journal of Artificial Intelligence Research and the Journal of Machine Learning Research and is currently President of the International Machine Learning Society. She is a recipient of NSERC's E.W.R. Steacie Memorial Fellowship (2018), a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI), a Senior Fellow of the Canadian Institute for Advanced Research (CIFAR) and in 2016 was named a member of the College of New Scholars, Artists and Scientists by the Royal Society of Canada.

Yoshua Bengio (U. Montreal)

More from the Same Authors