Collaborative research: CIF: small: inverse reinforcement learning with heterogeneous data: estimation algorithms with finite time and sample guarantees
Active Project Grant Awarded
- Award ID
- 2641665
- Recipient
-
Rector & Visitors Of The University Of Virginia UEI JJG6HU8PA4S5
- Awarding agency
-
Division of Computing and Communication Foundations
National Science Foundation
- Obligated
- $173,700
Award facts
- Assistance listing
- 47.070 Computer and Information Science and Engineering
- Completion date 17% complete
- Place of performance
- Charlottesville, VA, USA
Award details come from USAspending.gov.
About this award
The National Science Foundation Division of Computing and Communication Foundations awarded Project Grant 2641665 to Rector & Visitors of the University of Virginia, doing business as University of Virginia, with $173,700 obligated on September 9, 2026, under the Computer and Information Science and Engineering program (CFDA 47.070). The program supports investigator-initiated research and education across computing, communications, and information science and engineering. This award funds a collaborative research project on inverse reinforcement learning with heterogeneous data, developing estimation algorithms with finite time and sample guarantees. The work builds machine learning models of an agent's dynamic decisions subject to structural constraints on observed behavior, capturing both the agent's reward function (preferences) and its representation of environment dynamics. These models support counterfactual analysis and transfer learning, and the project states that its outcomes apply to control systems, natural language processing, and autonomous driving. The project also includes reinforcement learning and optimization curriculum enhancement, engagement of students from diverse backgrounds in cross-disciplinary research, and K-12 outreach. The period of performance runs from September 9, 2026 to November 30, 2027, with place of performance in Charlottesville, Virginia.
Description
- Abstract
- Learning a structural model of dynamic decision-making helps US better understand and predict how agents, whether human or machine, make decisions over time in changing environments. Instead of just copying actions, this approach allows US to capture both the agent?S goals (PREFERENCES) and how IT understands the world (environment DYNAMICS). This provides a much deeper insight into behavior, enabling predictions about how the agent would act in new or unseen situations. Such models are valuable because they can help improve decision-making systems, allowing them to adapt and make reliable choices in complex real-world scenarios, such as personalized AI assistants, autonomous systems, or decision support tools. There is an urgent need for models and algorithms that can create such structural frameworks. The outcomes of this project will have broad applications, including areas like control systems, natural language processing, and autonomous driving. Moreover, these efforts offer valuable opportunities to enhance the optimization and reinforcement learning curriculum, engaging students from diverse backgrounds in cross-disciplinary research and K12 outreach initiatives. This project develops machine learning models of an agent?S dynamic decisions subject to structural constraints on observed behavior. Specifically, the agent?S observed behavior (DATA) is modeled as being consistent with the inter-temporal optimization of a reward function (PREFERENCES) given a representation of how the environment evolves pursuant to control actions (DYNAMICS). Unlike behavioral cloning models, a structural model of observed control behavior is a solid basis to perform counterfactual analysis and/or transfer learning. However, developing structural models of control is computationally challenging and the statistical properties of structural estimators are not easy to characterize. This project aims to advance the state-of-the-art on methodologies for learning structural models of control, by considering a diverse set of DATA (including demonstration and PREFERENCES), and by considering both online and offline settings. Finally, extensive experiments will be conducted to evaluate and apply the proposed methodologies in aligning large language models (LLMS), and in autonomous driving. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are not planned for this award.
Quick answers
Who received award 2641665?
2641665 was awarded to Rector & Visitors Of The University Of Virginia by Division of Computing and Communication Foundations (National Science Foundation) on September 9, 2026.
How much is award 2641665 worth?
$173,700 has been obligated on 2641665.
On GovTribe
See this award's full record
- Every transaction and subaward
- The recipient's other awards and teaming partners
- Similar grant awards
- Ask GovTribe AI about this award