Bayesian Inference of Temporal Specifications to Explain How Plans Differ

Anonymous

Keywords: Specification Mining, Explainable AI Planning, Contrastive Explanations, Bayesian Inference

TL;DR: We present a Bayesian inference model to infer contrastive explanations (as LTL specifications) describing how two sets of plan traces differ.

Abstract: Temporal logics are useful for describing dynamic system behavior, and have been successfully used as a language for goal definitions during task planning. Prior works on inferring temporal logic specifications have focused on "summarizing" the input dataset -- i.e., finding specifications that are satisfied by all plan traces belonging to the given set. In this paper, we examine the problem of inferring specifications that describe temporal differences between two sets of plan traces. We formalize the concept of providing such contrastive explanations, then present a Bayesian probabilistic model for inferring contrastive explanations as linear temporal logic specifications. We demonstrate the efficacy, scalability, and robustness of our model for inferring correct specifications across various benchmark planning domains and for a simulated air combat mission.