no code implementations • 7 Feb 2024 • Davide Corsi, Guy Amir, Guy Katz, Alessandro Farinelli
In recent years, Deep Reinforcement Learning (DRL) has become a popular paradigm in machine learning due to its successful applications to real-world and complex systems.
no code implementations • 18 Aug 2023 • Luca Marzari, Davide Corsi, Enrico Marchesini, Alessandro Farinelli, Ferdinando Cicalese
Identifying safe areas is a key point to guarantee trust for systems that are based on Deep Neural Networks (DNNs).
no code implementations • 31 Jul 2023 • Shahaf Bassan, Guy Amir, Davide Corsi, Idan Refaeli, Guy Katz
We evaluate our approach on two popular benchmarks from the domain of automated navigation; and observe that our methods allow the efficient computation of minimal and minimum explanations, significantly outperforming the state of the art.
no code implementations • 17 Jan 2023 • Luca Marzari, Davide Corsi, Ferdinando Cicalese, Alessandro Farinelli
Due to the #P-completeness of the problem, we also propose a randomized, approximate method that provides a provable probabilistic bound of the correct count while significantly reducing computational requirements.
no code implementations • 20 Jun 2022 • Davide Corsi, Raz Yerushalmi, Guy Amir, Alessandro Farinelli, David Harel, Guy Katz
Deep reinforcement learning (DRL) has achieved groundbreaking successes in a wide variety of robotic applications.
no code implementations • 26 May 2022 • Guy Amir, Davide Corsi, Raz Yerushalmi, Luca Marzari, David Harel, Alessandro Farinelli, Guy Katz
Our work is the first to establish the usefulness of DNN verification in identifying and filtering out suboptimal DRL policies in real-world robots, and we believe that the methods presented here are applicable to a wide range of systems that incorporate deep-learning-based agents.
1 code implementation • 23 Dec 2021 • Luca Marzari, Davide Corsi, Enrico Marchesini, Alessandro Farinelli
To this end, we present a CL approach that leverages Transfer of Learning (ToL) and fine-tuning in a Unity-based simulation with the Robotnik Kairos as a robotic agent.
no code implementations • 16 Dec 2021 • Enrico Marchesini, Davide Corsi, Alessandro Farinelli
Aquatic navigation is an extremely challenging task due to the non-stationary environment and the uncertainties of the robotic platform, hence it is crucial to consider the safety aspect of the problem, by analyzing the behavior of the trained network to avoid dangerous situations (e. g., collisions).
no code implementations • ICLR 2021 • Enrico Marchesini, Davide Corsi, Alessandro Farinelli
The combination of Evolutionary Strategies (ES) and Deep Reinforcement Learning (DRL) has been recently proposed to merge the benefits of both solutions.
no code implementations • 19 Oct 2020 • Davide Corsi, Enrico Marchesini, Alessandro Farinelli
In this paper, we present a semi-formal verification approach for decision-making tasks, based on interval analysis, that addresses the computational demanding of previous verification frameworks and design metrics to measure the safety of the models.