I am an associate professor and the Corrie and Jim Furber ’64 faculty fellow at the Industrial and Systems Engineering Department in Texas A&M University. I also affilated with the Electrical and Computer Engineering Department (by courtesy). I am also a 2023 Texas A&M Institute of Data Science (TAMIDS) Career Initiation Fellow and a recipient of NSF CAREER in 2023.
I received my Ph.D. in Electrical and Systems Engineering from the University of Pennsylvania in 2015 under the supervision of Alejandro Ribeiro. I was subsequently a Postdoctoral Fellow at the Georgia Institute of Technology affiliated with both the School of Electrical & Computer Engineering and the School of Biological Sciences hosted by Jeff S. Shamma and Joshua S. Weitz. For further information, see Curriculum Vitae and Google Scholar.
The research interests of Networked Multiagent Systems (NetMaS) lab focus on understanding and designing networked interactions of agents in social and technological settings. Examples of such complex systems are found in energy systems (microgrid, demand response), public health (infectious diseases), autonomous robot systems, communication (uplink power allocation), and in many other cyber-physical systems. Broadly, theoretical interests of the lab are at the confluence of game theory, distributed optimization, signal processing and control theory. We invite you to visit the Research section for a more detailed explanation of research themes of the lab. You can find the specific research papers in Publications.
Recent Preprints and Publications
- A Distributed and Coupled Policy Gradient Algorithm for Networked Multi-Agent Reinforcement Learning with P. Dai, D. Wang, S. Aydin, W. Yu
- Actor-critic based reinforcement learning for multi-stage process planning and end point control in abrasive finishing operations with A. Karthikeyan, L. D. Kashyap and S. Bukkapatnam
- Almost Sure Convergence of Networked Policy Gradient Play over Time-Varying Networks in Markov Potential Games with S. Aydin
- Learning Nash in Constrained Markov Games with an $\alpha$-Potential by S. Das
- Simulation-Based Optimistic Policy Iteration In Multi-Agent Games with Kullback-Leibler Control Cost by K. Nakhleh
I am looking for outstanding PhD candidates with a solid background on Engineering, or Applied Mathematics. The candidate is expected conduct theoretical and algorithmic research on control, multi-agent systems, game theory, and optimization. The application areas of interest are autonomous teams, epidemics, or smart grids!