collaborators

2 papers

eess.SY2026

Sample-Efficient Model-Free Policy Gradient Methods for Stochastic LQR via Robust Linear Regression

Bowen Song, Sebastien Gros, Andrea Iannelli

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient…

math.OC2025

Optimization-based Coordination of Traffic Lights and Automated Vehicles at Intersections

Azita Dabiri, Giray Önür, Sebastien Gros +1

This paper tackles the challenge of coordinating traffic lights and automated vehicles at signalized intersections, formulated as a constrained finite-horizon optimal control probl…