We present MILABOT: a deep reinforcement learning chatbot developed at
MILA for the Amazon Alexa Prize competition. MILABOT is capable of
conversing with humans on popular small talk topics through both speech
and text. The system consists of an ensemble of natural language
generation and retrieval models, including sequence-to-sequence and latent
variable neural network models. By applying reinforcement learning to
crowd-sourced data and real-world user interactions, the system has been
trained to select an appropriate response from the models in its ensemble.
The system has been evaluated through A/B testing with real-world users,
where it performed excellent compared to competing systems.