Analyzing Adversarial Inputs in Deep Reinforcement Learning

D Corsi, G Amir, G Katz, A Farinelli - ar** safe and explainable autonomous agents: from simulation to the real world
F Bianchi, A Castellini, A Farinelli, L Marzari… - CEUR WORKSHOP …, 2024 - iris.univr.it
Responsible artificial intelligence is the next challenge of research to foster the deployment
of autonomous systems in the real world. In this paper, we focus on safe and explainable …

Safeguarding and Empowering General Purpose Robots through Abstraction and Constraint Certification

T Wei - 2024 - search.proquest.com
Robots are increasingly deployed across various domains, from industrial automation to
domestic assistance. Ensuring that robots operate safely and intelligently is crucial to …

Enhancing Linear Bound Tightness in Neural Network Verification via Sampling-Based Underestimation

L Marzari, F Cicalese, A Farinelli - openreview.net
We present $\texttt {PT-LiRPA} $(Probabilistically Tightened LiRPA), a novel approach that
enhances existing linear relaxation-based perturbation analysis (LiRPA) methods for neural …