Samantha Krening

Papers

Total Citations

102

H-Index

About

Samantha Krening is a leading researcher in interactive machine learning and human-robot interaction, with a focus on making artificial intelligence accessible to non-experts. Her work centers on enabling robots and intelligent agents to learn from natural human instruction—such as spoken advice and sentiment—without requiring users to have machine learning expertise or adhere to rigid vocabularies. In her highly cited paper “Learning From Explanations Using Sentiment and Advice in RL” (83 citations), she pioneered methods for reinforcement learning agents to interpret and act on human explanations that lack explicit state information, bridging the gap between intuitive human communication and algorithmic learning. Her research also explores how design choices in AI systems influence perceived intelligence, as detailed in “Characteristics that Influence Perceived Intelligence in AI Design” (16 citations), offering crucial insights for creating more trustworthy and effective interactive agents. Additionally, her work on object-focused advice in reinforcement learning advances the use of simple, natural sentences for training. Krening’s contributions are vital for developing robots that can be seamlessly taught by everyday users, with her citation record reflecting significant impact in the field of human-centered AI.