Quoc Phong Nguyen

About

Quoc Phong Nguyen is a researcher whose work lies at the intersection of machine learning, optimization, and risk-aware decision-making. His primary research areas include inverse reinforcement learning (IRL), Bayesian optimization, and risk-sensitive optimization under uncertainty. Nguyen’s most notable contribution is his pioneering approach to IRL, where he introduced a method for efficiently exploring reward functions using Bayesian optimization—addressing the fundamental ill-posedness of IRL by systematically searching the space of plausible rewards. This work, published in 2020, has already garnered 7 citations and is relevant to critical applications such as value alignment in AI and robot learning from demonstration. In parallel, Nguyen has made significant strides in risk management with his 2021 paper on Value-at-Risk (VaR) optimization using Gaussian processes. He developed the V-UCB algorithm, which provides the first no-regret guarantee for maximizing VaR of a black-box function—a breakthrough for high-stakes domains like finance and engineering where quantifying tail risks is essential. With 3 citations to date, this work underscores his ability to bridge theoretical guarantees with practical risk-aware optimization. Nguyen’s research is characterized by its rigor and real-world relevance, making him a rising voice in safe and efficient AI systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Efficient Exploration of Reward Functions in Inverse Reinforcement\n Learning via Bayesian Optimization

   7 citations · 2020
2. 2
   Value-at-Risk Optimization with Gaussian Processes

   3 citations · 2021

Key Collaborators

Contact & Links