UNIVERSITY PARK, Pa. — Aron Laszka, assistant professor in the Penn State College of Information Sciences and Technology (IST), earned a five-year, $685,588 U.S. National Science Foundation (NSF) Early Career Development (CAREER) Award for his project “Scaling Deep Reinforcement Learning for Societal-Scale Cyber-Physical Systems.”
In this Q&A, Laszka discussed his goals for the project.
Q: What do you want to understand or solve through this project?
Laszka: Societal-scale cyber-physical systems — such as smart transportation networks and electric power grids — are essential to modern, everyday life. These systems combine physical infrastructure with thousands of sensors and devices that monitor and control them.
However, managing these massive, distributed systems in real time poses a significant challenge that must be addressed to enable these systems to reach their full potential. Deep reinforcement learning (DRL) shows promise as an artificial intelligence (AI) tool for controlling cyber-physical systems. However, current DRL methods have trouble handling systems at this scale and dealing with limits on communication among their many parts.
This project aims to solve the problems of scale and limited communication in large systems. The goal is to create a new communication-aware DRL framework tailored to large, distributed systems. It will break complex systems into smaller, easier-to-manage parts and enable them to communicate efficiently, even under real-world network constraints. This approach will help use data-driven decisions to better manage critical infrastructure.
Q: How will advances in this area impact society?
Laszka: This research has the potential to directly improve the performance, efficiency and resilience of the critical infrastructures we rely on every day.
In the transportation domain, these advances could reduce traffic congestion, make on-demand transit more reliable and help emergency services respond faster. In the energy sector, the project outcomes may contribute to a more stable and efficient electric grid and better use of distributed power generation.
Ultimately, improving these large systems could boost the economy, support sustainability and make communities safer.
Q: How will undergraduate and/or graduate students contribute to this research?
Laszka: Both undergraduate and graduate students will play a central role in this interdisciplinary research endeavor. We will recruit and mentor undergraduate students through programs such as the Pennsylvania Space Grant Undergraduate Research Internship Program, enabling them to gain hands-on experience across the full STEM research lifecycle. Graduate students will be fundamental to the research thrusts, engaging with both artificial intelligence theory and real-world cyber-physical system challenges, preparing them to be leading experts in academia or industry.
Students will also help translate our research into interactive, "gamified" learning modules for K-12 outreach that intuitively illustrate the challenges of infrastructure systems and artificial intelligence. Through these educational and outreach activities, we will build a strong pipeline of future STEM researchers.
Q: The CAREER award recognizes your potential as a researcher, educator and leader in the field. How do you hope to fulfill that potential?
Laszka: This CAREER award is a critical foundation for my long-term vision of establishing a nationally recognized research and education program focused on AI-driven decision-making for human-centered, societal-scale systems. Building upon this foundational framework, I intend to tackle future challenges like AI alignment and explainable AI to ensure that as our infrastructure becomes more intelligent, it remains transparent and firmly in the service of human and societal well-being. I also aim to establish a vertically integrated talent pipeline, from high school students to doctoral scholars. By actively integrating research into education and outreach, I hope to empower the future workforce and streamline the transfer of artificial intelligence technology into practical, societal benefits.
Penn State is shaping the future of higher education in the age of artificial intelligence. Our focus is on human-centered, ethical AI innovation that delivers meaningful impacts for Penn State and the broader community. Through visionary planning, strategic partnerships, targeted hiring and strategic investments, we will equip every Penn State student, staff and faculty member with the AI-related knowledge, experience and confidence they need to succeed in the AI-powered future. Learn more at Penn State's website on AI.