Project Grant FA95502410152

This National Science Foundation project grant of $146,801 will support research into new approaches for modeling games of incomplete information from July 2022 through June 2025. Funded under the Social, Behavioral, and Economic Sciences program, the research aims to develop robust predictive tools for strategic situations where outcomes depend on unobserved states and players receive private signals. Specifically, the grant will further generalized solution concepts that characterize...

The National Science Foundation awarded a $294,401 Project Grant to the University of Chicago under the Social, Behavioral, and Economic Sciences program (CFDA 47.075). The grant supports research developing new tools for robust predictions in strategic games with incomplete information. Specifically, the researchers will generalize the solution concept of Bayesian correlated equilibrium to characterize rationalizable behavior under common prior beliefs about unobserved payoff-relevant states....

This $281,964 National Science Foundation project grant supports research at the University of Texas at Dallas to investigate mean field games and mean field control in the context of supervised and deep learning. Specifically, the three-year award under the NSF's Mathematical and Physical Sciences program (CFDA 47.049) will examine applying mean field control theory to replace empirical data distributions with joint probability distributions between inputs and outputs in machine learning...

The University of Michigan was awarded a $330,000 Project Grant from the National Science Foundation Division of Mathematical Sciences. The grant supports the project "NEW DEVELOPMENTS IN MEAN FIELD GAME THEORY AND APPLICATIONS" from September 1, 2021 through August 31, 2024. The project aims to advance mean field game theory and explore its applications. Mean field game theory analyzes strategic interactions among large numbers of rational individuals and has wide-ranging applications...

This $599,744 federal Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program supports research by Yale University to develop new theory and methods for analyzing, training, and designing complex, high-dimensional multi-agent games and machine learning systems. The key activities under this 3-year award include: Developing optimal uncoupled algorithms for computing and learning equilibria in high-dimensional concave games...

This Project Grant from the National Science Foundation's Computer and Information Science and Engineering program provides $599,986 to Stanford University for research titled "Machine Learning with Behavioral and Social Data." The five-year award beginning in August 2022 will support the development of new machine learning algorithms that model human decision-making descriptively based on behavioral data. The researcher aims to build on recent advances in modeling choices as driven by...

This $600,000 National Science Foundation project grant supports research at Stony Brook University to develop a suite of novel distributed reinforcement learning algorithms. The grant is funded through the NSF's Computer and Information Science and Engineering program. Specifically, the three-year award will fund research to establish theoretical foundations for designing, analyzing, and applying fully distributed reinforcement learning algorithms over large-scale networks without global...

The National Science Foundation (NSF) awarded a Project Grant under the Mathematical and Physical Sciences (CFDA 47.049) program to The Trustees of Princeton University's Office of Research and Project Administration, totaling $320,000 and spanning July 1, 2024 to June 30, 2027. The grant supports research on mean field optimal control and differential game theory, which have applications across diverse fields including social sciences, economics, and engineering. Key objectives include...

This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) in the amount of $398,990 provides funding to the University of California, Irvine to conduct research exploring the theoretical foundations of multi-agent learning systems. The project aims to develop computationally efficient algorithms that can provably converge to equilibrium states in multi-agent environments, particularly in scenarios involving both cooperative...

This National Science Foundation (NSF) Project Grant award under the Social, Behavioral, and Economic Sciences (CFDA 47.075) program provides $163,588 to the University of Texas at Dallas (UTD) to investigate how individuals learn about situations and personality traits, and how this situational and trait learning influences decision-making. The research team will leverage behavioral methods, neuroimaging techniques, and computational modeling to (1) identify the neural and cognitive...