Zobrazeno 1 - 10
of 8 364
pro vyhledávání: '"Abate, P ."'
Subversion Strategy Eval: Evaluating AI's stateless strategic capabilities against control protocols
AI control protocols are plans for usefully deploying AI systems in a way that is safe, even if the AI intends to subvert the protocol. Previous work evaluated protocols by subverting them with a human-AI red team, where an AI follows the human-writt
Externí odkaz:
http://arxiv.org/abs/2412.12480
In this paper, we present a novel framework to synthesize robust strategies for discrete-time nonlinear systems with random disturbances that are unknown, against temporal logic specifications. The proposed framework is data-driven and abstraction-ba
Externí odkaz:
http://arxiv.org/abs/2412.11343
Autor:
Skalse, Joar, Abate, Alessandro
The aim of inverse reinforcement learning (IRL) is to infer an agent's preferences from observing their behaviour. Usually, preferences are modelled as a reward function, $R$, and behaviour is modelled as a policy, $\pi$. One of the central difficult
Externí odkaz:
http://arxiv.org/abs/2412.11155
In light of the inherently complex and dynamic nature of real-world environments, incorporating risk measures is crucial for the robustness evaluation of deep learning models. In this work, we propose a Risk-Averse Certification framework for Bayesia
Externí odkaz:
http://arxiv.org/abs/2411.19729
Autor:
Skalse, Joar, Abate, Alessandro
The aim of Inverse Reinforcement Learning (IRL) is to infer a reward function $R$ from a policy $\pi$. This problem is difficult, for several reasons. First of all, there are typically multiple reward functions which are compatible with a given polic
Externí odkaz:
http://arxiv.org/abs/2411.15951
Autor:
Abate, Nicolás, Torroba, Gonzalo
We prove the irreversibility of the renormalization group for quantum field theory in de Sitter space in $d=2$, $3$ and $4$ space-time dimensions. The proof is based on strong subadditivity of the entanglement entropy, de Sitter invariance, and the M
Externí odkaz:
http://arxiv.org/abs/2411.08961
Autor:
Pan, Yi, Jiang, Hanqi, Chen, Junhao, Li, Yiwei, Zhao, Huaqin, Zhou, Yifan, Shu, Peng, Wu, Zihao, Liu, Zhengliang, Zhu, Dajiang, Li, Xiang, Abate, Yohannes, Liu, Tianming
Neuromorphic computing has emerged as a promising energy-efficient alternative to traditional artificial intelligence, predominantly utilizing spiking neural networks (SNNs) implemented on neuromorphic hardware. Significant advancements have been mad
Externí odkaz:
http://arxiv.org/abs/2410.09674
A crucial capability of Machine Learning models in real-world applications is the ability to continuously learn new tasks. This adaptability allows them to respond to potentially inevitable shifts in the data-generating distribution over time. Howeve
Externí odkaz:
http://arxiv.org/abs/2410.07812
Autor:
Mathiesen, Frederik Baymler, Romao, Licio, Calvert, Simeon C., Laurenti, Luca, Abate, Alessandro
In this paper, we present a novel data-driven approach to quantify safety for non-linear, discrete-time stochastic systems with unknown noise distribution. We define safety as the probability that the system remains in a given region of the state spa
Externí odkaz:
http://arxiv.org/abs/2410.06662
Linear temporal logic (LTL) has recently been adopted as a powerful formalism for specifying complex, temporally extended tasks in reinforcement learning (RL). However, learning policies that efficiently satisfy arbitrary specifications not observed
Externí odkaz:
http://arxiv.org/abs/2410.04631