Siavash Alemzadeh

I’m a PhD candidate in the Robotics, Aerospace, Information, and Networks (RAIN) lab located at the William E. Boeing department of Aeronautics and Astronautics. Before that, I completed my undergraduate in Mechanical Engineering from Sharif University of Technology in 2014 and my master’s degree in Mechanical Engineering from University of Washington in 2016. I am also enrolled in a concurrent master’s degree in Applied Mathematics at University of Washington. I am passionate about solving new problems using tools from engineering, mathematics, and simulations. I am interested in both theoretic and applied aspects of problems in machine learning, reinforcement learning, and control theory. I am also curious about large-scale planning and control of real-world systems such as robotics swarms, infrastructure platforms, transportation, and social networks. My portfolio spans a wide range of numerical and theoretical analysis of data-driven control and reinforcement learning for multiagent settings. In my leisure time, I watch and play soccer, play the piano, cook, and read.

Links:             

Education
PhD in Aeronautics and Astronautics University of Washington 2015-Present
MS in Applied Mathematics University of Washington 2018-present
MS in Mechanical Engineering University of Washington 2014-2016
BS in Mechanical Engineering Sharif University of Technology 2009-2014
Work Experience
Research Intern at Honda Research Institute, San Jose CA, 2020
Research Intern at NEC Laboratories America, San Jose CA, 2019
Research Interests
Machine Learning for Control Reinforcement Learning
Multiagent Systems Distributed Control and Optimization
Publications
Adaptive Traffic Control with Deep Reinforcement Learning: Towards State-of-the-art and Beyond
Siavash Alemzadeh , Ramin Moslemi, Ratnesh Sharma, Mehran Mesbahi		 Submitted Link Code
On Regularizability and its Application to OnlineControl of Unstable LTI Systems
Shahriar Talebi, Siavash Alemzadeh , Newsha Rahimi, Mehran Mesbahi		 Submitted Link Code
Deep Learning-based Resource Allocation for Infrastructure Resilience
Siavash Alemzadeh , Hesam Talebiyan, Shahriar Talebi, Leonardo Duenas-Osorio, Mehran Mesbahi		 ICTAI 2020 Link Code
Online Regulation of Unstable LTI Systems from a Single Trajectory
Shahriar Talebi, Siavash Alemzadeh , Newsha Rahimi, Mehran Mesbahi		 CDC 2020 Link Code
Distributed Learning in Network Games: a Dual Averaging Approach
Shahriar Talebi, Siavash Alemzadeh , Lillian Ratliff, Mehran Mesbahi		 CDC 2019Link-
Distributed Q-Learning for Dynamically Decoupled Systems
Siavash Alemzadeh , Mehran Mesbahi		 ACC 2019Link-
Influence Models on Layered Uncertain Networks: A Guaranteed-Cost Design Perspective
Siavash Alemzadeh , Mehran Mesbahi		 CDC 2018Link-
Linear Model Regression on Time-series Data: Non-asymptotic Error Bounds and Applications
Atiye Alaeddini, Siavash Alemzadeh , Afshin Mesbahi, Mehran Mesbahi		 CDC 2018 Link-
Controllability and Data-Driven Identification of Bipartite Consensus on Nonlinear Signed Networks
Mathias Hudoba de Badyn, Siavash Alemzadeh , Mehran Mesbahi		 CDC 2017 Link-
Controllability and Stabilizablity Analysis of Signed Consensus Networks
Siavash Alemzadeh , Mathias Hudoba de Badyn, Mehran Mesbahi		 CCTA 2017 Link-
Talks
Resource Allocation for Infrastructure Resilience using Artificial Neural Networks ICTAI 2020-
Distributed Q-Learning for Dynamically Decoupled Systems Microsoft ResearchLink
Applications of Networked Dynamical Systems in Social Networks Guest Lecture - Networked Systems Link
Optimization and Control for the Resilience of the Interdependent Networks NSF CRISP Workshop Link
Distributed Q-Learning for Dynamically Decoupled Systems ACC 2019 Link
A Compositional Approach for Modeling and Control of Layered Networks INFORMS 2018 Link
Influence Models on Layered Uncertain Networks: A Guaranteed-Cost Perspective CDC 2018 Link
Controllability and Stabilizablity Analysis of Signed Consensus Networks CCTA 2017 Link