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
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 …
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 …
domestic assistance. Ensuring that robots operate safely and intelligently is crucial to …
Enhancing Linear Bound Tightness in Neural Network Verification via Sampling-Based Underestimation
We present $\texttt {PT-LiRPA} $(Probabilistically Tightened LiRPA), a novel approach that
enhances existing linear relaxation-based perturbation analysis (LiRPA) methods for neural …
enhances existing linear relaxation-based perturbation analysis (LiRPA) methods for neural …