Collaborative Research: CIF: Medium: MoDL:Toward a Mathematical Foundation of Deep Reinforcement Learning

NSF Award Search · 01002223DB NSF RESEARCH & RELATED ACTIVIT · $300,000 · view on nsf.gov ↗

Abstract

Deep Reinforcement Learning (DRL), which uses neural networks to solve sequential decision-making problems, has made breakthroughs in real-world applications, such as robotics, gaming, healthcare, and transportation systems. However, current theoretical work on reinforcement learning is restricted to problems with a small number of states; as these results do not cover neural networks, they cannot be used to satisfactorily explain the empirical successes of DRL. This project seeks to bridge this gap by building a mathematical foundation for DRL that leverages ideas from approximation theory, control theory, and optimization theory. This will allow the computational and statistical complexity of DRL to be systematically characterized, and will help with designing more efficient and reliable empirical methods. Education and outreach plans are integrated into this project. Specifically, the investigators will mentor graduate and undergraduate students (some through the STARS program for underrepresented groups at the University of washington), develop new courses and monographs, organize research workshops, and develop course materials for a high school data science and artificial intelligence curriculum. This project has three major components. The first thrust identifies which types of guarantees are achievable by policies for different reinforcement learning problem instances. Concretely, this requires investigating how increasingly structured problem instances enable str

Key facts

NSF award ID
2539753
Awardee
University of California-Berkeley (CA)
SAM.gov UEI
GS3YEVSS12N6
PI
Jason Lee
Primary program
01002223DB NSF RESEARCH & RELATED ACTIVIT
All programs
Machine Learning Theory, SPECIAL PROJECTS - CCF, MEDIUM PROJECT, SIGNAL PROCESSING
Estimated total
$300,000
Funds obligated
$249,987
Transaction type
Standard Grant
Period
07/01/2025 → 09/30/2026