People increasingly rely on machine learning (ML) to make intelligent decisions. However, the ML results are often difficult to interpret and the algorithms do not support interaction to solicit clarification or explanation. In this paper, we highlight an emerging research area of interpretable explanations for transfer learning in sequential tasks, in which an agent must explain how it learns a new task given prior, common knowledge. The goal is to enhance a user's ability to trust and use the system output and to enable iterative feedback for improving the system. We review prior work in probabilistic systems, sequential decision-making, interpretable explanations, transfer learning, and interactive machine learning, and identify an intersection that deserves further research focus. We believe that developing adaptive, transparent learning models will build the foundation for better human-machine systems in applications for elder care, education, and health care.

We propose a new problem we refer to as goal recognitiondesign ( grd) , in which we take a domain theory and a set ofgoals and ask the following questions: to what extent do theactions performed by an agent within the model reveal its objective, and what is the best way to modify a model so thatany agent acting in the model reveals its objective as early aspossible. Our contribution is the introduction of a new measure we call worst case distinctiveness ( wcd ) with which weassess a  grd model. The  wcd represents the maximal lengthof a prefix of an optimal path an agent may take within a system before it becomes clear at which goal it is aiming. Tomodel and solve the  grd problem we choose to use the models and tools from the closely related field of automated planning. We present two methods for calculating the  wcd of a grd model, one of which is based on a novel compilation to aclassical planning problem. We then propose a way to reducethe  wcd of a model by limiting the set of available actions anagent can perform and provide a method for calculating theoptimal set of actions to be removed from the model. Our empirical evaluation shows the proposed solution to be effectivein computing and minimizing  wcd .