Project Grant 2533865
- Federal Project Grant Award Summary Texas A&M Engineering Experiment Station received a $300,000 Project Grant from the National Science Foundation's Directorate for Engineering (CFDA 47.041) awarded July 1, 2026, through June 30, 2029, to develop decentralized multi-agent reinforcement learning (MARL) algorithms for constrained Markov games. The research will establish mathematical foundations and provably convergent algorithms that enable multiple autonomous decision-makers—such as robots,...
- Federal Grant Award Summary The National Science Foundation (NSF) Directorate for Engineering awarded $224,996 to the New Jersey Institute of Technology (NJIT) on July 1, 2026, for a collaborative research project titled "Reinforcement Learning with High-Probability Safety Constraints: Theory, and Applications" (CFDA 47.041). The three-year project, concluding June 30, 2029, will deliver foundational theory, algorithms, and software tools that enable safe reinforcement learning (RL)...
- This National Science Foundation (NSF) Division of Electrical, Communications and Cyber Systems award, CFDA 47.041 Engineering, will provide $193,000 from September 1, 2024 to August 31, 2027 to New York University (NYU) to develop new theories and methodologies for safe reinforcement learning in domains such as robotics, autonomous driving, and power systems. The key products and services to be delivered under this Project Grant include: 1) Formulating safety measures as general objectives...
- Federal Grant Award Summary The National Science Foundation (NSF) Directorate for Engineering awarded the University of Texas at Arlington $299,963 on July 15, 2026, through its Engineering program (CFDA 47.041) to support collaborative research on scaling robust multi-agent systems. The project, which runs through June 30, 2029, will develop efficient learning methods and decentralized algorithms that enable autonomous multi-agent systems to perform reliably in real-world environments. The...
- This Project Grant award from the National Science Foundation's Engineering program (CFDA 47.041) provides $356,488 to the Texas A&M Engineering Experiment Station (Tees) to develop a resilient reinforcement learning (RL) framework for managing heterogeneous multi-agent systems in complex and structured environments. The research aims to produce scalable and computationally-efficient RL algorithms with rigorous convergence and complexity analysis for applications like interference management...
- Federal Project Grant Award Summary Rensselaer Polytechnic Institute received a $360,000 project grant awarded September 1, 2025, through the National Science Foundation (NSF) Engineering program (CFDA 47.041), with completion targeted for August 31, 2028. Funded by NSF's Division of Electrical, Communications and Cyber Systems, this project delivers a theoretically principled framework for performing accurate hypothetical interventions on complex large networked systems—including...
- This $375,000 federal Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) program (CFDA 47.070). The goal of the project is to develop tools and methods to help ensure the safe operation of autonomous systems that utilize reinforcement learning (RL) algorithms. Key activities include: 1) developing inverse RL algorithms to learn an agent's reward function from demonstrations, 2) exploring the agent's norms to...
- This $749,963 Project Grant was awarded by the National Science Foundation (NSF) Division of Computing and Communication Foundations on October 1, 2023. The grant is funded under the NSF's Computer and Information Science and Engineering (CFDA #47.070) program, which supports investigator-initiated research and education across all areas of computing, communications, and information science and engineering. The grant was awarded to Northeastern University, a private, non-profit research...
- The National Science Foundation (NSF) awarded a $194,000 Project Grant under the Engineering program (CFDA 47.041) to Georgia Tech Research Corp to conduct research on safe reinforcement learning. The project aims to develop new approaches for training, improving, and evaluating reinforcement learning policies that are robust to distribution shift and non-stationarity, with the goal of ensuring safety in applications such as robotics, autonomous driving, and power systems. Key innovations...
- Federal Project Grant Award Summary Rensselaer Polytechnic Institute received a $299,990 Project Grant from the National Science Foundation's Division of Civil, Mechanical, and Manufacturing Innovation under the Engineering program (CFDA 47.041) awarded September 1, 2025, with completion targeted for August 31, 2028. The award funds development of the Linked Ensemble Aggregation Procedure (LEAP), a novel optimization algorithm designed to address critical gaps in the optimization of chaotic...
Grant Summary Rensselaer Polytechnic Institute received a $299,935 collaborative research Project Grant awarded July 1, 2026, through the National Science Foundation's Directorate for Engineering (CFDA 47.041). The award funds research on decentralized multi-agent reinforcement learning (MARL) algorithms designed to enable autonomous decision-makers—such as robots, energy resources, and actuators—to learn safe and efficient operation in dynamic, uncertain environments without requiring a central coordinator. The project develops provably convergent MARL algorithms that explicitly incorporate operational, safety, and resource constraints into learning dynamics, addressing the fundamental challenge of ensuring that decentralized systems achieve coordination while providing rigorous performance and safety guarantees in complex, competitive settings applicable to teams of robots and distributed energy systems. The three-year effort (completion date June 30, 2029) emphasizes establishing new mathematical foundations for safe multi-agent learning and advancing national priorities in trustworthy artificial intelligence and autonomous systems. Broader impacts include integrating research outcomes into undergraduate and graduate curricula, mentoring students, organizing academic events focused on safe multi-agent learning, and conducting outreach activities to broaden participation in STEM fields. The work addresses a critical gap in existing approaches that typically assume full information sharing or ignore constraints during learning, thereby extending applicability to real-world decentralized systems where individual components operate on limited local information.
Mod # | Description | ReasonForModification | Federal Obligation | Date |
|---|---|---|---|---|
| Not listed | $299.9k | 6/23/26 |