no code implementations • 15 Dec 2023 • Sara Maria Brancato, Davide Salzano, Francesco De Lellis, Davide Fiore, Giovanni Russo, Mario di Bernardo
Our work showcases the viability of learning-based strategies for the control of cellular density in bioreactors, making a step forward toward their use for the control of the composition of microbial consortia.
1 code implementation • 16 Nov 2023 • Francesco De Lellis, Marco Coraggio, Giovanni Russo, Mirco Musolesi, Mario di Bernardo
In addressing control problems such as regulation and tracking through reinforcement learning, it is often required to guarantee that the acquired policy meets essential performance and stability criteria such as a desired settling time and steady-state error prior to deployment.
no code implementations • 7 Nov 2023 • Veronica Centorrino, Anand Gokhale, Alexander Davydov, Giovanni Russo, Francesco Bullo
Our analysis leverages contraction theory to characterize the behavior of a family of firing-rate competitive networks for sparse reconstruction with and without non-negativity constraints.
no code implementations • 24 Jun 2023 • Emiland Garrabe, Hozefa Jesawada, Carmen Del Vecchio, Giovanni Russo
This paper is concerned with a finite-horizon inverse control problem, which has the goal of inferring, from observations, the possibly non-convex and non-stationary cost driving the actions of an agent.
no code implementations • 2 Dec 2022 • Francesco De Lellis, Marco Coraggio, Giovanni Russo, Mirco Musolesi, Mario di Bernardo
One of the major challenges in Deep Reinforcement Learning for control is the need for extensive training to learn the policy.
no code implementations • 7 Jun 2022 • Shihao Xie, Giovanni Russo
We consider both leaderless and leader-follower, possibly nonlinear, networks affected by time-varying communication delays.
no code implementations • 11 Apr 2022 • Sara Maria Brancato, Francesco De Lellis, Davide Salzano, Giovanni Russo, Mario di Bernardo
We investigate the problem of using a learning-based strategy to stabilize a synthetic toggle switch via an external control approach.
no code implementations • 15 Feb 2022 • Shihao Xie, Giovanni Russo
Specifically, we propose the use of a multiplex architecture to design distributed control protocols to reject polynomial disturbances up to ramps and guarantee a scalability property that prohibits the amplification of residual disturbances.
1 code implementation • 21 Dec 2021 • Enrico Ferrentino, Pasquale Chiacchio, Giovanni Russo
Contrary to other approaches, the pipeline we present: (i) does not need the constraints to be fulfilled in the possibly noisy example data; (ii) enables control synthesis even when the data are collected from an example system that is different from the one under control.
1 code implementation • 25 Mar 2021 • Marco Coraggio, Shihao Xie, Francesco De Lellis, Giovanni Russo, Mario di Bernardo
This paper is concerned with the design of intermittent non-pharmaceutical strategies to mitigate the spread of the COVID-19 epidemic exploiting network epidemiological models.
no code implementations • 12 Dec 2020 • Francesco De Lellis, Giovanni Russo, Mario di Bernardo
We introduce a control-tutored reinforcement learning (CTRL) algorithm.
no code implementations • 12 Jun 2020 • Shihao Xie, Giovanni Russo, Richard Middleton
This paper is concerned with the study of scalability in nonlinear heterogeneous networks affected by communication delays and disturbances.
no code implementations • 15 May 2020 • Fabio Della Rossa, Davide Salzano, Anna Di Meglio, Francesco De Lellis, Marco Coraggio, Carmela Calabrese, Agostino Guarino, Ricardo Cardona, Pietro DeLellis, Davide Liuzza, Francesco Lo Iudice, Giovanni Russo, Mario di Bernardo
Using the model, we confirm the effectiveness at the regional level of the national lockdown strategy implemented so far by the Italian government to mitigate the spread of the disease and show its efficacy at the regional level.
Physics and Society Populations and Evolution 93C10, 92D30, 92D25 J.2
no code implementations • 12 Dec 2019 • Francesco De Lellis, Fabrizia Auletta, Giovanni Russo, Piero De Lellis, Mario di Bernardo
We introduce a control-tutored reinforcement learning (CTRL) algorithm.
no code implementations • 26 Nov 2019 • Francesco De Lellis, Fabrizia Auletta, Giovanni Russo, Mario di Bernardo
In this extended abstract we introduce a novel control-tutored Q-learning approach (CTQL) as part of the ongoing effort in developing model-based and safe RL for continuous state spaces.
1 code implementation • 11 Nov 2019 • Meghana Rathi, Pietro Ferraro, Giovanni Russo
In this paper we propose a new approach to complement reinforcement learning (RL) with model-based control (in particular, Model Predictive Control - MPC).