1 citations · 2 across the 4 of their papers we have counts for
6 papers
PAGE-PG: A Simple and Loopless Variance-Reduced Policy Gradient Method with Probabilistic Gradient Estimation
Matilde Gargiani, Andrea Zanelli, Andrea Martinelli +2
Despite their success, policy gradient methods suffer from high variance of the gradient estimate, which can result in unsatisfactory sample complexity. Recently, numerous variance…
Parallel and Flexible Dynamic Programming via the Randomized Mini-Batch Operator
Matilde Gargiani, Andrea Martinelli, Max Ruts Martinez +1
The Bellman operator constitutes the foundation of dynamic programming (DP). An alternative is presented by the Gauss-Seidel operator, whose evaluation, differently from that of th…
On the Synthesis of Bellman Inequalities for Data-Driven Optimal Control
Andrea Martinelli, Matilde Gargiani, John Lygeros
In the context of the linear programming (LP) approach to data-driven control, one assumes that the dynamical system is unknown but can be observed indirectly through data on its e…
Passivity-based Decentralized Control for Discrete-time Large-scale Systems
Ahmed Aboudonia, Andrea Martinelli, John Lygeros
Passivity theory has recently contributed to developing decentralized control schemes for large-scale systems. Many decentralized passivity-based control schemes are designed in co…
Control of Networked Systems by Clustering: The Degree of Freedom Concept
Andrea Martinelli, John Lygeros
We address the problem of local flux redistribution in networked systems. The aim is to detect a suitable cluster which is able to locally adsorb a disturbance by means of an appro…
Data-driven optimal control with a relaxed linear program
Andrea Martinelli, Matilde Gargiani, John Lygeros
The linear programming (LP) approach has a long history in the theory of approximate dynamic programming. When it comes to computation, however, the LP approach often suffers from…