Towards Contrastive Explanations for Comparing the Ethics of Plans

We are interested in models where actions are deterministic, This can be done through contrastive explanations [5], durationless, and can be performed one at a time. We also which focus on explaining the difference between a factual assume a known initial state and goal. Traditionally, ethical event A and a contrasting event B. To produce these explanations, principles of single decisions are evaluated [1]. In the context one must reason about the hypothetical alternative B, of AI Planning this means analysing a massive number of which likely means constructing an alternative plan where B isolated decisions that may not make sense without the is included rather than A. The original model is constrained context in which they are being made. Therefore, it is to produce a hypothetical planning model (HModel). The preferable to evaluate the ethical contents of a plan as a solution to the HModel is the hypothetical plan (HPlan) that whole. Lindner et al. [2] describe an approach to judging contains the contrast case expected by the user.