Goal-Conditioned Recommendations of AI Explanations

Saptarashmi Bandyopadhyay, Vibhu Agrawal, Sarah Savidge, Eric Krokos, John P Dickerson

Keywords: Goal-conditioned Reinforcement Learning, Explainable AI (XAI), SlateQ, Recommender Systems

TL;DR: SlateQ based recommendation system is used to simulate appropriate Explainable AI (XAI) outcomes aligned with user requirement and conditioned on the goals achieved by the specific AI models.

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.

Confirmation: I have read and confirm that at least one author will be attending the workshop in person if the submission is accepted

Submission Number: 34