no code implementations • 29 Jan 2023 • Nicolas Lanzetti, Efe C. Balta, Dominic Liao-McPherson, Florian Dörfler
Since estimation problems can be posed as optimization problems in the probability space, we devise a stochastic projected Wasserstein gradient flow that keeps track of the belief of the estimated quantity and can consume samples from online data.
no code implementations • 20 Oct 2022 • Antonio Terpin, Nicolas Lanzetti, Batuhan Yardim, Florian Dörfler, Giorgia Ramponi
In this paper, we explore optimal transport discrepancies (which include the Wasserstein distance) to define trust regions, and we propose a novel algorithm - Optimal Transport Trust Region Policy Optimization (OT-TRPO) - for continuous state-action spaces.
no code implementations • 12 Sep 2022 • Nicolas Lanzetti, Joudi Hajar, Florian Dörfler
The study of complex political phenomena such as parties' polarization calls for mathematical models of political systems.
no code implementations • 3 Sep 2021 • Nicolas Lanzetti, Maximilian Schiffer, Michael Ostrovsky, Marco Pavone
Cities worldwide struggle with overloaded transportation systems and their externalities.
no code implementations • 28 Jun 2021 • Gioele Zardini, Nicolas Lanzetti, Marco Pavone, Emilio Frazzoli
We provide a comprehensive review of methods and tools to model and solve problems related to autonomous mobility-on-demand systems.
no code implementations • 19 Aug 2020 • Gioele Zardini, Nicolas Lanzetti, Andrea Censi, Emilio Frazzoli, Marco Pavone
This requires tools to study such a coupling and co-design mobility systems in terms of different objectives.