報告時間：1月8日（周一）晚上20:00-21:00
報告地點：騰訊會議 715-780-860
報告人：美國威廉與瑪麗學院 陳海鵬 助理教授
主持人：王萬元
報告摘要：Decision-making has been critical in socially important domains like population health. Typical examples include epidemics control and network-based preventative health, where the decision-making problems essentially have a network or combinatorial structure. This class of decision-making problems are highly challenging because of the exponentially large solution spaces. The challenge has been amplified by real-world characteristics of population health, such as stochasticity, sequential decision-making, and unknown constraints/objectives. In this talk, I will show how these combinatorial optimization problems can be formulated as Markov decision processes (MDPs), and how to design novel reinforcement learning methods to solve these problems.
報告人簡介：Haipeng Chen is currently an assistant professor at College of William and Mary. Prior to that, he did his postdocs at Harvard University and Dartmouth College. He obtained the PhD at Nanyang Technological University and the BS from the University of Science and Technology of China. His primary research interest lies in AI for social impact: for AI techniques, he focuses on reinforcement learning, prediction, and optimization; for social domains, he is interested in health and environment. He has 20+ publications in premier AI and data science conferences (e.g., AAAI, IJCAI, NeurIPS, AAMAS, UAI, KDD, and ICDM) or journals (e.g., IEEE/ACM Transactions). His research has been recognized with the best paper nomination at AAMAS-2021, Innovation Demonstration Award runner-up at IJCAI-2019, and winner of the 2017 Microsoft Malmo Collaborative AI Challenge. As part of his research agenda, he has established partnerships with non-profits such as Lackey Clinic, The Family Van, Mobile Health Map, Safe Place for Youth, and Wadhwani
