About Me

I am a PhD student in the Dialogue Systems and Machine Learning group at Heinrich Heine University in Düsseldorf. My research focuses on dialogue policy optimisation using reinforcement learning, with application to multi-domain task-oriented dialogue systems. I am particularly interested in sample efficient policy optimisation and dynamic policy modelling. I am also interested in meta-learning methods for fast adaptation, reward function learning, continual learning, state and action representation learning and general reinforcement learning methods.