Luca Marzari

According to our database, Luca Marzari authored at least 15 papers between 2021 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

ModelVerification.jl: a Comprehensive Toolbox for Formally Verifying Deep Neural Networks.

Tianhao Wei, Luca Marzari, Kai S. Yun, Hanjiang Hu, Peizhi Niu, Xusheng Luo, Changliu Liu

CoRR, 2024

Improving Policy Optimization via ε-Retrain.

Luca Marzari, Changliu Liu, Priya L. Donti, Enrico Marchesini

CoRR, 2024

Developing safe and explainable autonomous agents: from simulation to the real world.

Federico Bianchi, Alberto Castellini, Alessandro Farinelli, Luca Marzari, Daniele Meli, Francesco Trotti, Celeste Veronese

Proceedings of the Ital-IA Intelligenza Artificiale, 2024

Rigorous Probabilistic Guarantees for Robust Counterfactual Explanations.

Luca Marzari, Francesco Leofante, Ferdinando Cicalese, Alessandro Farinelli

Proceedings of the ECAI 2024 - 27th European Conference on Artificial Intelligence, 19-24 October 2024, Santiago de Compostela, Spain, 2024

Enumerating Safe Regions in Deep Neural Networks with Provable Probabilistic Guarantees.

Luca Marzari, Davide Corsi, Enrico Marchesini, Alessandro Farinelli, Ferdinando Cicalese

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing.

Luca Marzari, Gabriele Roncolato, Alessandro Farinelli

CoRR, 2023

Verifying Learning-Based Robotic Navigation Systems.

Guy Amir, Davide Corsi, Raz Yerushalmi, Luca Marzari, David Harel, Alessandro Farinelli, Guy Katz

Proceedings of the Tools and Algorithms for the Construction and Analysis of Systems, 2023

Safe and Efficient Reinforcement Learning for Environmental Monitoring.

Federico Bianchi, Davide Corsi, Luca Marzari, Daniele Meli, Francesco Trotti, Maddalena Zuccotto, Alberto Castellini, Alessandro Farinelli

Proceedings of the Italia Intelligenza Artificiale, 2023

Constrained Reinforcement Learning and Formal Verification for Safe Colonoscopy Navigation.

Davide Corsi, Luca Marzari, Ameya Pore, Alessandro Farinelli, Alicia Casals, Paolo Fiorini, Diego Dall'Alba

IROS, 2023

The #DNN-Verification Problem: Counting Unsafe Inputs for Deep Neural Networks.

Luca Marzari, Davide Corsi, Ferdinando Cicalese, Alessandro Farinelli

Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, 2023

Online Safety Property Collection and Refinement for Safe Deep Reinforcement Learning in Mapless Navigation.

Luca Marzari, Enrico Marchesini, Alessandro Farinelli

Proceedings of the IEEE International Conference on Robotics and Automation, 2023

Safe Deep Reinforcement Learning by Verifying Task-Level Properties.

Enrico Marchesini, Luca Marzari, Alessandro Farinelli, Christopher Amato

Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems, 2023

Scaling #DNN-Verification Tools with Efficient Bound Propagation and Parallel Computing (regular paper).

Luca Marzari, Gabriele Roncolato, Alessandro Farinelli

Proceedings of the 10th Italian Workshop on Artificial Intelligence and Robotics co-located with the the 22nd International Conference of the Italian Association for Artificial Intelligence (AIxIA 2023), 2023

2022

Curriculum learning for safe mapless navigation.

Luca Marzari, Davide Corsi, Enrico Marchesini, Alessandro Farinelli

Proceedings of the SAC '22: The 37th ACM/SIGAPP Symposium on Applied Computing, Virtual Event, April 25, 2022

2021

Towards Hierarchical Task Decomposition using Deep Reinforcement Learning for Pick and Place Subtasks.

Luca Marzari, Ameya Pore, Diego Dall'Alba, Gerardo Aragon-Camarasa, Alessandro Farinelli, Paolo Fiorini

Proceedings of the 20th International Conference on Advanced Robotics, 2021