Duke University

The high-level goals of our group are to help build decision-support systems (recommender systems, decision aid, search...) and automatic decision systems (autonomous agents, robots, traders...). Our research work lies at the intersection of artificial intelligence, decision theory, machine learning and operations research. In particular, it deals with (sequential) decision making under uncertainty, multiobjective optimization, preference elicitation/learning.

Currently, we focus in particular on deep reinforcement learning with the goal of (1) improving its algorithms (e.g., more sample-efficient, more generalizable), (2) extending the framework to novel settings (e.g., fair optimization, learning from human feedback), or (3) applying it to various application domains (e.g., combinatorial optimization, material design).