This $300,000 federal Project Grant, awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, supports a collaborative research project on inverse reinforcement learning with heterogeneous data. The project aims to develop machine learning models for capturing an agent's dynamic decision-making process, including both their preferences (reward function) and understanding of the environment (dynamics). This structural modeling approach can enable more insightful behavior prediction and adaptation, with potential applications in areas like personalized AI assistants, autonomous systems, and decision support tools. The project activities will also engage students and support K-12 outreach initiatives to enhance optimization and reinforcement learning curriculum. The award period runs from December 1, 2024 to November 30, 2027, and is being led by the Regents of the University of Minnesota.
Generated 3/25/25, 2:45 AM