Watch the recording here.

Abstract: Many real-world problems demand robust AI models that integrate learning and planning for an agent—or a team of agents—operating against adversaries in multi-agent environments with limited data. In such complex settings, it is crucial to anticipate both the strategic behavior of adversaries and the adversarial manipulations that can degrade learning performance and decision quality. In this talk, I will discuss the challenges of modeling adversarial decision-making and ensuring the security of machine learning in data-driven, competitive multi-agent environments with sparse observations. I will present algorithms we have developed to address these challenges, drawing on techniques from reinforcement learning, game theory, and optimization. I will also highlight real-world applications of our methods in domains such as wildlife protection and public health.

Bio: Thanh Nguyen is an Associate Professor in the Computer Science department at the University of Oregon (UO). Prior to UO, she was a postdoc at the University of Michigan and earned her Ph.D. in Computer Science from the University of Southern California. Thanh’s work in the field of Artificial Intelligence is motivated by real-world societal problems, particularly in the areas of Public Safety and Security, Conservation, and Public Health. She brings together techniques from multi-agent systems, reinforcement learning, and game theory to solve problems in those areas, with the focus on studying adversary behavioral learning and deception in competitive multi-agent environments. Thanh’s work has been recognized by multiple awards, including the IAAI-16 Deployed Application Award, and the AAMAS-16 Runner-up of the Best Innovative Application Paper Award. Her works in wildlife protection and public health were evaluated and/or deployed in multiple countries around the world.