Maryam Kamgarpour

Edit profile

maryam.kamgarpour@epfl.ch +41 21 693 57 30 https://www.epfl.ch/labs/sycamore

EPFL STI IGM SYCAMORE
ME C1 400 (Bâtiment ME)
Station 9
1015 Lausanne

+41 21 693 57 30
Office: ME C1 400
EPFL > STI > IGM > SYCAMORE

Web site: Web site: https://www.epfl.ch/labs/sycamore/

+41 21 693 57 30
EPFL > STI > STI-SGM > SGM-ENS

vCard
Administrative data

Biography

short:
Maryam Kamgarpour holds a Doctor of Philosophy in Engineering from the University of California, Berkeley and a Bachelor of Applied Science from University of Waterloo, Canada. Her research is on safe decision-making and control under uncertainty, game theory and mechanism design, mixed integer and stochastic optimization and control. Her theoretical research is motivated by control challenges arising in intelligent transportation networks, robotics, power grid systems and healthcare. She is the recipient of NASA High Potential Individual Award, NASA Excellence in Publication Award, and the European Union (ERC) Starting Grant.

long:
Maryam Kamgarpour is a professor in the School of Engineering of École Polytechnique Fédérale de Lausanne. Prior to EPFL, she served as a faculty at the University of British Columbia and at ETH Zürich. She holds a Doctor of Philosophy in Engineering from the University of California, Berkeley and a Bachelor of Applied Science from University of Waterloo, Canada. Her research is on stochastic control and multiagent learning and control. Her theoretical research is motivated by fascinating control problems arising in intelligent transportation systems, robotics, and power grid systems.

She was awarded the European Union Starting Grant (2016-2021) to advance her research on control and game theory for integrating renewable energy into the power system. Her work on distributed control received the IEEE Transactions on Control of Network Systems Outstanding Paper Award (2022). She collaborated with NASA on safe and fuel-efficient aircraft trajectory design, and for this work received the NASA High Potential Individual Award (2010).

She is passionate about understanding and addressing fundamental problems in control, and mentoring students to work with her on these problems. Her publications have contributed to theory of hybrid systems (reachability, safety and optimal control), distributed control (the role of information structure), game theory (learning equilibria under bandit feedback), mechanism design (coalition-proofness, price of anarchy), safe zeroth-order learning, inverse reinforcement learning and multiagent reinforcement learning.

Publications

Infoscience publications

Infoscience

Safe optimization with grey-box information: Application to composites autoclave processing improvement on the fly

M. A. Roohi; M. Ramezankhani; M. Kamgarpour; A. S. Milani

Composites Part C: Open Access. 2025. Vol. 16, p. 100560. DOI : 10.1016/j.jcomc.2025.100560.

Maryam Kamgarpour

Biography

Publications

Infoscience publications

Infoscience

Safe optimization with grey-box information: Application to composites autoclave processing improvement on the fly

Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm

Aircraft Trajectory Planning for Climate Hotspot Avoidance Considering Air Traffic Complexity: A Constrained Multi-Agent Reinforcement Learning Approach

Recursively Feasible Chance-Constrained Model Predictive Control Under Gaussian Mixture Model Uncertainty

Learning to bid in forward electricity markets using a no-regret algorithm

Payoff-Based Learning of Nash Equilibria in Merely Monotone Games

Multi-Agent Learning in Contextual Games under Unknown Constraints

Reinforcement learning for scaffold-free construction of spanning-structures

Certification of Bottleneck Task Assignment With Shortest Path Criteria

Constrained Inverse Reinforcement Learning: Challenges and Solutions for Real World Implementation

Provable Convergence Guarantees for Constrained Inverse Reinforcement Learning

Multi-agent Reinforcement Learning for Assembly of a Spanning Structure

Learning to make mixed-integer robot motion planning easy

Identifiability and Generalizability in Constrained Inverse Reinforcement Learning

Multi-robot task allocation for safe planning against stochastic hazard dynamics

Safe Zeroth-Order Optimization Using Linear Programs

Safe Zeroth-Order Convex Optimization Using Quadratic Local Approximations

Data-Driven Control and Optimization under Noisy and Uncertain Conditions

Enabling inter-area reserve exchange through stable benefit allocation mechanisms *

Iterative Graph Deformation for Aircraft Trajectory Planning Considering Ensemble Forecasting of Thunderstorms

Optimal Task Assignment and Collision Avoidance for Mobile Robots

Coordination and control of a group of ground robots

Chance-Constrained Trajectory Planning With Multimodal Environmental Uncertainty

System-level, input-output and new parameterizations of stabilizing controllers, and their numerical computation

Safe Motion Planning against Multimodal Distributions Based on a Scenario Approach

Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation

Fast Projection Onto Convex Smooth Constraints

Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems

Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems

Multi-robot task allocation for safe planning against stochastic hazard dynamics

A comment on performance guarantees of a greedy algorithm for minimizing a supermodular set function on comatroid

Informed scenario-based RRT∗ for aircraft trajectory planning under ensemble forecasting of thunderstorms

On the Equivalence of Youla, System-Level, and Input-Output Parameterizations

Bandit Online Learning of Nash Equilibria in Monotone Games

Optimal Linear Controller for Minimizing DC Voltage Oscillations in MMC-Based Offshore Multiterminal HVDC Grids

A market-based approach for enabling inter-area reserve exchange

RRT*-Based Algorithm for Trajectory Planning Considering Probabilistic Weather Forecasts

Performance guarantees of forward and reverse greedy algorithms for minimizing nonsupermodular nonsubmodular functions on a matroid

Actuator Placement for Structural Controllability beyond Strong Connectivity and towards Robustness

Trajectory planning under environmental uncertainty with finite-sample safety guarantees

Learning the Globally Optimal Distributed LQ Regulator

Safe non-smooth black-box optimization with application to policy search

First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance

Mixed Strategies for Robust Optimization of Unknown Objectives

Distributed Design for Decentralized Control using Chordal Decomposition and ADMM

System-level, Input-output and New Parameterizations of Stabilizing Controllers, and Their Numerical Computation

Minimizing Regret of Bandit Online Optimization in Unconstrained Action Spaces

Core-Selecting Mechanisms in Electricity Markets

Safe Mission Planning under Dynamical Uncertainties

No-Regret Learning from Partially Observed Data in Repeated Auctions

Learning to Play Sequential Games versus Unknown Opponents

Sparsity Invariance for Convex Design of Distributed Controllers

Actuator Placement under Structural Controllability using Forward and Reverse Greedy Algorithms

Contextual Games: Multi-Agent Learning with Side Information

Enabling inter-area reserve exchange through stable benefit allocation mechanisms

Unified Approach to Convex Robust Distributed Control Given Arbitrary Information Structures

Learning Nash Equilibria in Monotone Games

Log Barriers for Safe Non-convex Black-box Optimization

Privacy of Real-Time Pricing in Smart Grid

Actuator Placement for Optimizing Network Performance under Controllability Constraints

Designing Coalition-Proof Reverse Auctions Over Continuous Goods

An Input–Output Parametrization of Stabilizing Controllers: Amidst Youla and System Level Synthesis

Exploiting structure of chance constrained programs via submodularity

Strengthening the Group: Aggregated Frequency Reserve Bidding With ADMM

Performance guarantees for greedy maximization of non-submodular controllability metrics

Using Uncertainty Data in Chance-Constrained Trajectory Planning

Robust aircraft trajectory planning under uncertain convective environments with optimal control and rapidly developing thunderstorms

On Separable Quadratic Lyapunov Functions for Convex Design of Distributed Controllers

Safe Convex Learning under Uncertain Constraints

Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature

Learning Generalized Nash Equilibria in a Class of Convex Games

Nash and Wardrop Equilibria in Aggregative Games With Coupling Constraints

No-Regret Learning in Unknown Games with Correlated Payoffs

Exploiting Weak Supermodularity for Coalition-Proof Mechanisms

Robust Distributed Control Beyond Quadratic Invariance