Automated Explanations for MDP Policies

Explaining policies of Markov Decision Processes (MDPs) is complicated due to their probabilistic and sequential nature. We present a technique to explain policies for factored MDP by populating a set of domain-independent templates. We also present a mechanism to determine a minimal set of templates that, viewed together, completely justify the policy. We demonstrate our technique using the problems of advising undergraduate students in their course selection and evaluate it through a user study.