A relational hierarchical model for decision-theoretic assistance

摘要

Building intelligent assistants has been a long-cherished goal of AI, and many were built and fine-tuned to specific application domains. In recent work, a domain-independent decision-theoretic model of assistance was proposed, where the task is to infer the user’s goal and take actions that minimize the expected cost of the user’s policy. In this paper, we extend this work to domains where the user’s policies have rich relational and hierarchical structure. Our results indicate that relational hierarchies allow succinct encoding of prior knowledge for the assistant, which in turn enables the assistant to start helping the user after a relatively small amount of experience.