A review of safe reinforcement learning: Methods, theory and applications

S Gu, L Yang, Y Du, G Chen, F Walter, J Wang… - arxiv preprint arxiv …, 2022‏ - arxiv.org
Reinforcement Learning (RL) has achieved tremendous success in many complex decision-
making tasks. However, safety concerns are raised during deploying RL in real-world …

Set propagation techniques for reachability analysis

M Althoff, G Frehse, A Girard - Annual Review of Control …, 2021‏ - annualreviews.org
Reachability analysis consists in computing the set of states that are reachable by a
dynamical system from all initial states and for all admissible inputs and parameters. It is a …

NNV: the neural network verification tool for deep neural networks and learning-enabled cyber-physical systems

HD Tran, X Yang, D Manzanas Lopez, P Musau… - … conference on computer …, 2020‏ - Springer
This paper presents the Neural Network Verification (NNV) software tool, a set-based
verification framework for deep neural networks (DNNs) and learning-enabled cyber …

NNV 2.0: the neural network verification tool

DM Lopez, SW Choi, HD Tran, TT Johnson - International Conference on …, 2023‏ - Springer
This manuscript presents the updated version of the Neural Network Verification (NNV) tool.
NNV is a formal verification software tool for deep learning models and cyber-physical …

Verification of deep convolutional neural networks using imagestars

HD Tran, S Bak, W **ang, TT Johnson - International conference on …, 2020‏ - Springer
Abstract Convolutional Neural Networks (CNN) have redefined state-of-the-art in many real-
world applications, such as facial recognition, image classification, human pose estimation …

Deep reinforcement learning verification: a survey

M Landers, A Doryab - ACM Computing Surveys, 2023‏ - dl.acm.org
Deep reinforcement learning (DRL) has proven capable of superhuman performance on
many complex tasks. To achieve this success, DRL algorithms train a decision-making agent …

The fourth international verification of neural networks competition (vnn-comp 2023): Summary and results

C Brix, S Bak, C Liu, TT Johnson - arxiv preprint arxiv:2312.16760, 2023‏ - arxiv.org
This report summarizes the 4th International Verification of Neural Networks Competition
(VNN-COMP 2023), held as a part of the 6th Workshop on Formal Methods for ML-Enabled …

Verisig 2.0: Verification of neural network controllers using taylor model preconditioning

R Ivanov, T Carpenter, J Weimer, R Alur… - … on Computer Aided …, 2021‏ - Springer
Abstract This paper presents Verisig 2.0, a verification tool for closed-loop systems with
neural network (NN) controllers. We focus on NNs with tanh/sigmoid activations and develop …

Efficient neural network verification via adaptive refinement and adversarial search

P Henriksen, A Lomuscio - ECAI 2020, 2020‏ - ebooks.iospress.nl
We propose a novel verification method for high-dimensional feed-forward neural networks
governed by ReLU, Sigmoid and Tanh activation functions. We show that the method is …

Formal certification methods for automated vehicle safety assessment

T Zhao, E Yurtsever, JA Paulson… - IEEE Transactions on …, 2022‏ - ieeexplore.ieee.org
Challenges related to automated driving are no longer focused on just the construction of
such automated vehicles (AVs) but also on assuring the safety of operation. Recent …