Goal-Conditioned Recommendations of AI Explanations

Saptarashmi Bandyopadhyay, Vibhu Agrawal, John P Dickerson

Abstract: The large-scale usage of Artificial Intelligence (AI) models has made it important to explain their outputs subject to requirements and goals for using these models. The definition of goals in Goal-conditioned Reinforcement Learning (GCRL) aligns with the task of recommending an appropriate explanation among Explainable AI (XAI) models like SHAP or LIME that is most interpretive for specific AI models. We focus on two goals of training random forest classifier to classify different training data in order to find appropriate explanations. SlateQ recommendation system is used for simulation where the underlying RecSim environment has a slate of documents with different quantity scores representing different goals.