The University of Arizona: Program in Applied Mathematics Colloquium – Scalable reinforcement learning for multi-agent networked systems

Presenter: Guannan Qu, Department of Electrical & Computer Engineering, Carnegie Mellon University

We study reinforcement learning (RL) in a setting with a network of agents whose states and actions interact in a local manner where the objective is to find policies such that the (discounted) global reward is maximized. A fundamental challenge in this setting is that the state-action space size scales exponentially in the number of agents, rendering the problem intractable for large networks. In this paper, we present our framework that exploits the network structure to conduct reinforcement learning in a scalable manner. The key feature in our framework is that we prove spatial decay properties for the Q function and the policy, meaning their dependence on faraway agents decays when the distance increases. Such spatial decay properties enable approximations by truncating the Q functions and policies to local neighborhoods, hence drastically reducing the dimension and avoiding the exponential blow-up in the number of agents.

The speaker will be in-person.


Math, 501 and Zoom Password:  applied

  • Audience: Adult, STEM Professional
  • Genre: Engineering, Mathematics
  • Type: Exhibit/Presentation


Apr 14 2023


2:30 pm - 3:30 pm



More Info

Register Here


Pima STEM Hub


Hybrid (Online & In-person)

Location 2

The University of Arizona Mathematics Building
617 N. Santa Rita Ave., Tucson, AZ, 85721


The University of Arizona College of Mathematics
(520) 621-6866
Register Here
QR Code