A University of Maryland expert in machine learning has been awarded funding from the National Science Foundation (NSF) to explore how autonomous systems can learn from each other and make decisions together in complex, real-world environments.
Kaiqing Zhang, an assistant professor of Electrical and Computer Engineering, is the principal investigator of an NSF Faculty Early Career Development Program (CAREER) award, totaling approximately $540,000 over the next five years.
This highly competitive award, one of NSF’s most prestigious for early-career faculty, recognizes researchers with the potential to serve as academic role models and drive advances in their fields.
Zhang holds an affiliate appointment in the University of Maryland Institute for Advanced Computer Studies and is a core faculty member in the University of Maryland Center for Machine Learning.
His project, “Foundations of Dynamic Multi-Agent Learning Under Information Constraints,” seeks to address a critical gap in understanding how multiple autonomous AI agents—such as self-driving cars, robots, and smart grid systems—can learn and collaborate in real-world settings.
These AI agents often operate with limited, noisy or delayed information, unlike traditional models that assume full knowledge of the environment. Zhang aims to develop strategies that help agents navigate uncertainty and make better decisions with only partial information.
To achieve this, he plans to draw on ideas from control theory, reinforcement learning, and game theory to refine how agents interact and adapt in dynamic environments. Zhang’s research will also explore how agents behave over time as they learn and make independent decisions in unpredictable scenarios.
Early findings suggest that sharing information strategically and using specialized training methods can significantly boost multi-agent learning. For example, exposing agents to extra information during training—beyond what they would encounter in real-world scenarios—has been shown to accelerate learning and enhance performance.
With applications in transportation, robotics, power grids, and logistics, Zhang’s work strives to enhance the efficiency and reliability of large-scale autonomous systems. By connecting theoretical principles with practical solutions, he plans to validate his algorithms through simulations and robotic platforms. Collaborating with industry partners, Zhang aims to turn these advances into real-world applications that address key technological and societal challenges.
Beyond advancing scientific knowledge, Zhang’s project will have broader impacts on education and outreach. It will include developing new courses on multi-agent dynamic learning, mentoring students in robotics competitions, and engaging underrepresented K-12 students to foster interest in machine learning and autonomous systems.
—Story by Melissa Brachfeld, UMIACS communications group
***
PI: Kaiqing Zhang, an assistant professor of Electrical and Computer Engineering with an affiliate appointment in the University of Maryland Institute for Advanced Computer Studies. Prior to this CAREER Award, his work has been recognized by several other awards, including the Simons-Berkeley Research Fellowship, CSL Thesis Award, ICML Outstanding Paper Award, and AAAI New Faculty Highlights.
About the CAREER award: The Faculty Early Career Development (CAREER) Program is an NSF activity that offers the foundation’s most prestigious awards in support of junior faculty who exemplify the role of teacher-scholars through outstanding research, excellent education and the integration of education and research within the context of the mission of their organization.