Deep Reinforcement Learning for Interactive Systems and Robots
October 11th 2017 10:45 - 11:00
Deep Reinforcement Learning (DRL) dialogue systems are attractive because they can jointly learn their feature representations and policies without manual feature engineering, but its successful application to real-world applications is not so straightforward. This talk will review steps already taken in this direction by reviewing recent research work on DRL-based spoken dialogue systems and DRL-based conversational robots. This talk will conclude with future potential work in academia and beyond.