Explainable Agency in Intelligent Agents: Doctoral Consortium

Explainability of intelligent agents has gained attention in recent years with their widespread utilization in society. Most work in Explainable AI (XAI) pay little attention to the humans that interact with these models, which risks resulting in unsatisfactory explanations. Theories of explainability and the nature of explanation has been widely explored in cognitive psychology and philosophy. This thesis aims to incorporate these insights to build explainable models and interfaces that can provide better and sufficient explanations to the interacting human.