Contrastive Learning from Exploratory Actions: Leveraging Natural Interactions for Preference Elicitation

N Dennler, S Nikolaidis, M Matarić - arxiv preprint arxiv:2501.01367, 2025 - arxiv.org
People have a variety of preferences for how robots behave. To understand and reason
about these preferences, robots aim to learn a reward function that describes how aligned …

On the Effect of Robot Errors on Human Teaching Dynamics

J Huang, I Sheidlower, RM Aronson… - Proceedings of the 12th …, 2024 - dl.acm.org
Human-in-the-loop learning is gaining popularity, particularly in the field of robotics,
because it leverages human knowledge about real-world tasks to facilitate agent learning …

How Much Progress Did I Make? An Unexplored Human Feedback Signal for Teaching Robots

H Yu, Q Fang, S Fang, RM Aronson… - 2024 33rd IEEE …, 2024 - ieeexplore.ieee.org
Enhancing the expressiveness of human teaching is vital for both improving robots' learning
from humans and the human-teaching-robot experience. In this work, we characterize and …