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

+41 21 693 57 30
EPFL > VPA-AVP-DLE > AVP-DLE-EDOC > EDEE-GE

Web site: Web site: https://go.epfl.ch/phd-edee

vCard

Biography

Maryam Kamgarpour is a professor in the School of Engineering of École Polytechnique Fédérale de Lausanne. Prior to joining EPFL, she served as a faculty at the University of British Columbia and at ETH Zürich. Her research focuses on advancing fundamental understanding of multi-agent decision-making in uncertain and dynamic environments. Towards this goal, she develops algorithms for safe stochastic control and reinforcement learning, and game theory and mechanism design. Her theoretical research is driven by control challenges arising in intelligent transportation networks, robotics and power grid systems.

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. She has received the NASA High Potential Individual Award and the NASA Excellence in Publication Award for her work on air traffic control with NASA Ames Research Center, and the European Union Starting Grant for her work on multi-agent decision making and distributed control for power systems. She is the recipient of the 2022 IEEE Transactions on Control of Network Systems Outstanding Paper Award and the 2024 European Control Award. She is a fellow of ELLIS and an associate editor of IEEE Transactions on Automatic Control.

Publications

Infoscience publications

Infoscience

Learning to Assemble with Alternative Plans

Z. Wang; W. Liu; J. Wang; G. Vallat; F. Shi et al.

ACM Transactions on Graphics. 2025. Vol. 44, num. 4, p. 1 - 16. DOI : 10.1145/3730824.

Maryam Kamgarpour

Biography

Publications

Infoscience publications

Infoscience

Learning to Assemble with Alternative Plans

Nash equilibria in scalar discrete-time linear quadratic games

Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design

A learning-based approach to stochastic optimal control under reach-avoid constraint

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

On the Convergence of Gradient Descent in Scalar Two-Agent Infinite-Horizon LQ Games

Chance-Constrained Linear Quadratic Gaussian Games for Multi-Robot Interaction Under Uncertainty

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

Provable Convergence Guarantees for Constrained Inverse Reinforcement Learning

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

Learning to make mixed-integer robot motion planning easy

Multi-agent Reinforcement Learning for Assembly of a Spanning Structure

Data-Driven Control and Optimization under Noisy and Uncertain Conditions

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

Identifiability and Generalizability in Constrained Inverse Reinforcement Learning

Safe Zeroth-Order Convex Optimization Using Quadratic Local Approximations

Safe Zeroth-Order Optimization Using Linear Programs

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

Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems

Fast Projection Onto Convex Smooth Constraints

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

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

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

Bandit Online Learning of Nash Equilibria in Monotone Games

Actuator Placement for Structural Controllability beyond Strong Connectivity and towards Robustness

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

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

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

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

Trajectory planning under environmental uncertainty with finite-sample safety guarantees

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

Learning the Globally Optimal Distributed LQ Regulator

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

Learning to Play Sequential Games versus Unknown Opponents

Contextual Games: Multi-Agent Learning with Side Information

Actuator Placement under Structural Controllability using Forward and Reverse Greedy Algorithms

Sparsity Invariance for Convex Design of Distributed Controllers

No-Regret Learning from Partially Observed Data in Repeated Auctions

Enabling inter-area reserve exchange through stable benefit allocation mechanisms

Log Barriers for Safe Non-convex Black-box Optimization

Actuator Placement for Optimizing Network Performance under Controllability Constraints

Unified Approach to Convex Robust Distributed Control Given Arbitrary Information Structures

Learning Nash Equilibria in Monotone Games

Privacy of Real-Time Pricing in Smart Grid

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

Using Uncertainty Data in Chance-Constrained Trajectory Planning

On Separable Quadratic Lyapunov Functions for Convex Design of Distributed Controllers

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

Performance guarantees for greedy maximization of non-submodular controllability metrics

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