Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Marchesini, Enrico"'
We present $\varepsilon$-retrain, an exploration strategy designed to encourage a behavioral preference while optimizing policies with monotonic improvement guarantees. To this end, we introduce an iterative procedure for collecting retrain areas --
Externí odkaz:
http://arxiv.org/abs/2406.08315
Autor:
Marzari, Luca, Corsi, Davide, Marchesini, Enrico, Farinelli, Alessandro, Cicalese, Ferdinando
Identifying safe areas is a key point to guarantee trust for systems that are based on Deep Neural Networks (DNNs). To this end, we introduce the AllDNN-Verification problem: given a safety property and a DNN, enumerate the set of all the regions of
Externí odkaz:
http://arxiv.org/abs/2308.09842
Autor:
Marchesini, Enrico, Amato, Christopher
Deep Policy Gradient (PG) algorithms employ value networks to drive the learning of parameterized policies and reduce the variance of the gradient estimates. However, value function approximation gets stuck in local optima and struggles to fit the ac
Externí odkaz:
http://arxiv.org/abs/2302.10145
Cost functions are commonly employed in Safe Deep Reinforcement Learning (DRL). However, the cost is typically encoded as an indicator function due to the difficulty of quantifying the risk of policy decisions in the state space. Such an encoding req
Externí odkaz:
http://arxiv.org/abs/2302.10030
Safety is essential for deploying Deep Reinforcement Learning (DRL) algorithms in real-world scenarios. Recently, verification approaches have been proposed to allow quantifying the number of violations of a DRL policy over input-output relationships
Externí odkaz:
http://arxiv.org/abs/2302.06695
This work investigates the effects of Curriculum Learning (CL)-based approaches on the agent's performance. In particular, we focus on the safety aspect of robotic mapless navigation, comparing over a standard end-to-end (E2E) training strategy. To t
Externí odkaz:
http://arxiv.org/abs/2112.12490
We propose a novel benchmark environment for Safe Reinforcement Learning focusing on aquatic navigation. Aquatic navigation is an extremely challenging task due to the non-stationary environment and the uncertainties of the robotic platform, hence it
Externí odkaz:
http://arxiv.org/abs/2112.10593
We study the problem of multi-robot mapless navigation in the popular Centralized Training and Decentralized Execution (CTDE) paradigm. This problem is challenging when each robot considers its path without explicitly sharing observations with other
Externí odkaz:
http://arxiv.org/abs/2112.09012
Autor:
Pore, Ameya, Corsi, Davide, Marchesini, Enrico, Dall'Alba, Diego, Casals, Alicia, Farinelli, Alessandro, Fiorini, Paolo
Deep Reinforcement Learning (DRL) is a viable solution for automating repetitive surgical subtasks due to its ability to learn complex behaviours in a dynamic environment. This task automation could lead to reduced surgeon's cognitive workload, incre
Externí odkaz:
http://arxiv.org/abs/2109.02323
Autor:
Geppert, Costanza, da Cruz, Mariana, Alma, Alberto, Andretta, Lucia, Anfora, Gianfranco, Battaglia, Donatella, Burgio, Giovanni, Caccavo, Vittoria, Chiesa, Serena Giorgia, Cinquatti, Francesca, Cocco, Arturo, Costi, Elena, D'Isita, Ilaria, Duso, Carlo, Garonna, Antonio Pietro, Germinara, Giacinto Salvatore, Bue, Paolo Lo, Lucchi, Andrea, Maistrello, Lara, Mannu, Roberto, Marchesini, Enrico, Masetti, Antonio, Mazzon, Luca, Mori, Nicola, Ortis, Giacomo, Peri, Ezio, Pescara, Guerino, Prazaru, Stefan Cristian, Ragone, Gianvito, Rigamonti, Ivo E., Rosi, Marzia Cristiana, Rotundo, Giuseppe, Sacchetti, Patrizia, Savoldelli, Sara, Suma, Pompeo, Tamburini, Giovanni, Garzia, Giovanna Tropea, Marini, Lorenzo
Publikováno v:
In Agricultural Systems March 2024 215