Explainable AI

If we are to welcome robots into our homes and trust them to make decisions on their own, they should perform well despite uncertainty and be able to clearly explain both what they are doing and why they are doing it in terms that both expert and non-expert users can understand. As learning (particularly deep learning) is increasingly used to inform decisions, it is both a practical and an ethical imperative that we ensure that data-driven systems are easy to inspect and audit both during development and after deployment. Our work aims to explore how we can make agents that both perform well and can explain their long-horizon decision-making process despite significant missing information.