Nicolas Huynh

About

Nicolas Huynh is a researcher specializing in reward learning, preference-based optimization, and human-robot interaction, with a particular focus on making artificial intelligence systems more aligned with human intentions. His most notable contribution, "Active Preference-Based Gaussian Process Regression for Reward Learning and Optimization" (2023), addresses one of the fundamental challenges in robotics and AI: how to design reward functions that accurately capture desired robot behaviors without requiring exhaustive manual specification. By leveraging Gaussian process regression combined with active learning strategies, Huynh's work enables systems to efficiently query human preferences and infer reward functions from comparisons rather than explicit demonstrations, significantly reducing the burden on human experts. This paper has accumulated 27 citations, reflecting growing interest in preference-based learning frameworks within the robotics and machine learning communities. His research sits at an important intersection of Bayesian optimization, interactive machine learning, and robot learning from human feedback — areas that have gained substantial momentum as the field moves toward more intuitive and scalable approaches to teaching autonomous systems. Huynh's contributions offer practical pathways for deploying robots in real-world environments where hand-crafted reward functions are impractical or infeasible.

Research Focus

Key Achievements

Top Papers

1. 1
   Active preference-based Gaussian process regression for reward learning and optimization

   27 citations · 2023

Key Collaborators

Contact & Links