Researchers at Florida Atlantic University’s College of Engineering and Computer Science have developed a new artificial intelligence framework designed to improve the management of complex systems with multiple decision-makers who operate at different levels of authority. The innovation, published in IEEE Transactions on Systems, Man and Cybernetics: Systems, is expected to impact smart energy grids, traffic networks, and autonomous vehicle systems.
Zhen Ni, Ph.D., senior author and associate professor in the Department of Electrical Engineering and Computer Science, explained the challenge: “These types of systems operate under a power hierarchy, where one player makes the first move and others must follow, and they’re more complicated than typical AI models assume. Traditional AI methods often treat every decision-maker as equal, operating at the same time with the same level of influence. While this makes for clean simulations, it doesn’t reflect how decisions are actually made in real-world scenarios – especially in environments full of uncertainty, limited bandwidth and uneven access to information.”
To address these issues, Ni worked with Xiangnan Zhong, Ph.D., first author and associate professor in the department. Their framework uses reinforcement learning—an approach that enables intelligent agents to learn from their environment over time—and incorporates two main innovations. The first is structuring decisions using a Stackelberg-Nash game model from game theory; this sets up a hierarchy where a “leader” acts first while “followers” respond optimally. This structure mirrors real-world situations such as energy management or connected transportation.
The second innovation involves an event-triggered mechanism that reduces computational demands by updating decisions only when necessary rather than at every time step. As Zhong stated: “Instead of constantly updating decisions at every time step, which is typical of many AI systems, our method updates decisions only when necessary, saving energy and processing power while maintaining performance and stability.”
This new system addresses both unequal decision-making power among agents and uncertainties arising from different levels of information access or predictability—a common situation in rapidly changing environments like smart grids or traffic control.
Stella Batalama, Ph.D., dean of the College of Engineering and Computer Science at FAU commented on the significance: “This work fills a crucial gap in the current AI landscape. By developing a method that reflects real-world decision hierarchies and adapts to imperfect information, Professors Zhong and Ni are helping us move closer to practical, intelligent systems that can handle the complexity of our modern infrastructure. The implications of this research are far-reaching. Whether it’s optimizing power consumption across cities or making autonomous systems more reliable, this kind of innovation is foundational to the future of intelligent technology. It represents a step forward not just for AI research, but for the everyday systems we depend on.”
According to simulation studies conducted by Zhong and Ni—which combined deep control theory with machine learning—their method maintains system stability while ensuring optimal strategies without unnecessary computation.
The project received support from both the National Science Foundation and United States Department of Transportation. The team plans further large-scale testing with hopes that their framework will eventually be integrated into operational city infrastructure for smarter resource management.
