On May 6th at 12:00 PM, the DEEC TALK “Policy Optimization in Reinforcement Learning” will take place. The session will be held in the EA1 amphitheater, North Tower, and will be conducted by Yuejie Chi, Charles C. and Dorothea S. Dilley Professor of Statistics and Data Science at Yale University, with a secondary appointment in Computer Science.

Abstract

Policy optimization, which aims to learn the policy of interest by maximizing the value function through large-scale optimization techniques, lies at the heart of modern reinforcement learning (RL). This talk will discuss the global convergence of policy gradient methods in single-agent, multi-agent, and federated settings, highlighting the role of preconditioning and regularization in enabling fast convergence.

About the speaker

Dr. Yuejie Chi is the Charles C. and Dorothea S. Dilley Professor of Statistics and Data Science at Yale University, with a secondary appointment in Computer Science, and a member of Yale Institute for Foundations of Data Science. She received her Ph.D. and M.A. from Princeton University, and B. Eng. (Hon.) from Tsinghua University, all in Electrical Engineering. Her research interests lie in the theoretical and algorithmic foundations of data science, generative AI, reinforcement learning, and signal processing, motivated by applications in scientific and engineering domains. Among others, Dr. Chi received the Presidential Early Career Award for Scientists and Engineers (PECASE), SIAM Activity Group on Imaging Science Best Paper Prize, IEEE Signal Processing Society Young Author Best Paper Award, and the inaugural IEEE Signal Processing Society Early Career Technical Achievement Award for contributions to high-dimensional structured signal processing. She is an IEEE Fellow (Class of 2023) for contributions to statistical signal processing with low-dimensional structures.