Enforcing hard constraints with soft barriers: Safe reinforcement learning in unknown stochastic environments
It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an
unknown and stochastic environment under hard constraints that require the system state …
unknown and stochastic environment under hard constraints that require the system state …
Verisig 2.0: Verification of neural network controllers using taylor model preconditioning
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 …
neural network (NN) controllers. We focus on NNs with tanh/sigmoid activations and develop …
NNV 2.0: the neural network verification tool
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 …
NNV is a formal verification software tool for deep learning models and cyber-physical …
Reachability analysis of neural feedback loops
Neural Networks (NNs) can provide major empirical performance improvements for closed-
loop systems, but they also introduce challenges in formally analyzing those systems' safety …
loop systems, but they also introduce challenges in formally analyzing those systems' safety …
Open-and closed-loop neural network verification using polynomial zonotopes
We present a novel approach to efficiently compute tight non-convex enclosures of the
image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation …
image through neural networks with ReLU, sigmoid, or hyperbolic tangent activation …
Verification of neural-network control systems by integrating Taylor models and zonotopes
C Schilling, M Forets, S Guadalupe - … of the AAAI Conference on Artificial …, 2022 - ojs.aaai.org
We study the verification problem for closed-loop dynamical systems with neural-network
controllers (NNCS). This problem is commonly reduced to computing the set of reachable …
controllers (NNCS). This problem is commonly reduced to computing the set of reachable …
Polar: A polynomial arithmetic framework for verifying neural-network controlled systems
We present POLAR (The source code can be found at https://github. com/ChaoHuang2018/
POLAR_Tool. The full version of this paper can be found at https://arxiv …
POLAR_Tool. The full version of this paper can be found at https://arxiv …
Trainify: A CEGAR-Driven Training and Verification Framework for Safe Deep Reinforcement Learning
P Jin, J Tian, D Zhi, X Wen, M Zhang - International Conference on …, 2022 - Springer
Abstract Deep Reinforcement Learning (DRL) has demonstrated its strength in developing
intelligent systems. These systems shall be formally guaranteed to be trustworthy when …
intelligent systems. These systems shall be formally guaranteed to be trustworthy when …
Reachability analysis of neural network control systems
Neural network controllers (NNCs) have shown great promise in autonomous and cyber-
physical systems. Despite the various verification approaches for neural networks, the safety …
physical systems. Despite the various verification approaches for neural networks, the safety …
Verifying controllers with vision-based perception using safe approximate abstractions
C Hsieh, Y Li, D Sun, K Joshi… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Fully formal verification of perception models is likely to remain challenging in the
foreseeable future, and yet these models are being integrated into safety-critical control …
foreseeable future, and yet these models are being integrated into safety-critical control …