MENU

Nicolas Lanzetti

NCCR – People
Nicolas Lanzetti

Wissenschaftliche Publikationen

Published
Stochastic Wasserstein Gradient Flows using Streaming Data with an Application in Predictive Maintenance
ArXiv
Nicolas Lanzetti, Efe Balta, Dominic Liao-McPherson, Florian Dörfler
Collection
Published
Co-Design to Enable User-Friendly Tools to Assess the Impact of Future Mobility Solutions
IEEE Transactions on Network Science and Engineering
Pages 1-18
Gioele Zardini, Nicolas Lanzetti, Andrea Censi, Emilio Frazzoli, Marco Pavone
Doi.org Collection
Published
Trust Region Policy Optimization with Optimal Transport Discrepancies: Duality and Algorithm for Continuous Actions
Proceedings of, the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)
Antonio Terpin, Nicolas Lanzetti, Batuhan Yardim, Florian Dörfler, Giorgia Ramponi
Doi.org Collection
Published
Analysis and Control of Autonomous Mobility-on-Demand Systems
Annual Review of Control, Robotics, and Autonomous Systems
Vol 5 Pages 633-658
Gioele Zardini, Nicolas Lanzetti, Marco Pavone, Emilio Frazzoli
Doi.org Collection
Published
Game Theory to Study Interactions between Mobility Stakeholders
24th IEEE International Conference on Intelligent Transportation Systems (ITSC)
Pages 2054-2061
Gioele Zardini, Nicolas Lanzetti, Laura Guerrini, Emilio Frazzoli, Florian Dörfler
Doi.org Collection

Forschungsprojekte als Forscher/-in

Titel
Leitende Forscher/-innen

Optimization Flows on Probability Distribution Spaces

Florian Dörfler

Zusammenfassung

We want to develop continuous-time optimality-seeking algorithms on the space of probability distributions. We envision our approach to result in practically useful algorithms to probabilistic (e.g. distributionally robust) optimization problems. Furthermore, our framework is directly applicable to optimization and control of traffic flow in a density modelling approach or a continuum modelling of multi-agent systems.

People involved

Florian Dörfler
NCCR – People
Florian Dörfler, Nicolas Lanzetti, , Saverio Bolognani
Optimization Flows on Probability Distribution Spaces
Florian Dörfler

We want to develop continuous-time optimality-seeking algorithms on the space of probability distributions. We envision our approach to result in practically useful algorithms to probabilistic (e.g. distributionally robust) optimization problems. Furthermore, our framework is directly applicable to optimization and control of traffic flow in a density modelling approach or a continuum modelling of multi-agent systems.

Florian Dörfler
NCCR – People
Florian Dörfler, Nicolas Lanzetti, , Saverio Bolognani
101
bcd7d27a-de53-49f7-949b-9a48b4ec7eb6