Project Grant 2441665
Award Date
9/1/25
Completion Date
8/31/30
Dollars Obligated
$476K
Federal Agency
Division of Information and Intelligent Systems
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Princeton, NJ, USA
Similar Awards
This $128,238 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research at the University of Texas at Austin to advance reinforcement learning (RL) through the development of a unified, principled off-policy algorithm framework. The research aims to enable more efficient, large-scale real-world sequential decision-making applications such as self-driving cars, industry automation, and natural...
This NSF Computer and Information Science and Engineering (CISE) Program (CFDA 47.070) Project Grant, awarded to Arizona State University in the amount of $598,123 on July 15, 2024, will develop new algorithms to enable AI systems to autonomously learn hierarchical world models and high-level actions. The goal is to create AI systems, such as hospital robots and disaster-recovery support systems, that can plan reliably and efficiently to accomplish complex user-desired tasks, without requiring...
This $439,425 federal Project Grant award was provided by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program. The grant supports research to enable the safe deployment of learning-enabled systems that can robustly learn and optimize their behavior based on uncertain human feedback and intent. The key objectives are to: (1) develop methods for providing probabilistic performance guarantees when learning policies from human input,...
This $299,999 Project Grant awarded by the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) supports research to enhance the performance of reinforcement learning (RL) systems in completing complex tasks in challenging environments. The project aims to develop new task and environment representations to enable active learning strategies that optimize resource allocation and reduce the need for extensive physical interactions with the...
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 National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Award (CFDA 47.070) for $600,000 supports the development of novel attention-based methods for partially observable reinforcement learning (PORL) at Northeastern University. The project aims to create advanced AI techniques, including attention-based model-free and model-based PORL approaches, to improve performance and sample efficiency in real-world partially observable domains such...
This Project Grant award of $279,640 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program supports research to develop mathematical foundations and algorithms for multi-task reinforcement learning. The project aims to address the challenge of data efficiency in reinforcement learning, which has limited its applicability in areas with limited data and computational resources. The research will explore conditions for joint learning of...
This Project Grant award, funded by the National Science Foundation's (NSF) Integrative Activities program (CFDA 47.083), will support the development of a specialized artificial intelligence (AI) foundation model for planning-like tasks. The $150,000 award, effective from February 1, 2025 to January 31, 2027, aims to create a compact and comprehensive AI model that can outperform and be more efficient at tasks requiring sequential decision-making, reasoning, and planning compared to the current...
This Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will provide $398,990.00 to the University of California, Irvine over 3 years starting on August 1, 2025. The project aims to develop a robust theoretical framework for analyzing learning processes in multi-agent systems, such as those found in autonomous driving, economics, and artificial intelligence applications. Key goals include designing...
This Project Grant award of $300,000 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program supports research on developing machine learning models for structural decision-making. The goal is to create models that can capture an agent's preferences and understanding of environmental dynamics, enabling better prediction and adaptation of decision-making in complex real-world scenarios. The research will explore methods for...