Published extensively in top-tier venues including ICML, NeurIPS, ICLR, SIOPT, and MOR
Notable works include: 'Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents' (ICML 2024)
'Provably Mitigating Overoptimization in RLHF' (NeurIPS 2024)
'Maximize to Explore: A Single Objective Fusing Estimation, Planning, and Exploration' (NeurIPS 2023, spotlight)
'Embed to Control Partially Observed Systems' (ICLR 2023)
'Reinforcement Learning from Partial Observation' (ICML 2022)
'Is Pessimism Provably Efficient for Offline RL?' (ICML 2021, later published in Mathematics of Operations Research 2024)
Multiple papers received Oral or Spotlight presentations
Background
Associate Professor in the Departments of Industrial Engineering & Management Sciences and Computer Science at Northwestern University
Affiliated with the Centers for Deep Learning and Optimization & Statistical Learning
Long-term research goal is to develop a new generation of data-driven decision-making methods, theory, and systems that tailor AI toward addressing societal challenges
Research focuses on: improving computational and statistical efficiency of autonomous learning agents; designing and optimizing societal-scale multi-agent systems involving human/robot cooperation and/or competition
Research interests span machine learning, optimization, statistics, game theory, and information theory