3 papers
cs.LG2024
Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems
Dapeng Zhi, Peixin Wang, Si Liu +2
The rapid advance of deep reinforcement learning techniques enables the oversight of safety-critical systems through the utilization of Deep Neural Networks (DNNs). This underscore…
cs.AI2023
Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales
Dapeng Zhi, Peixin Wang, Cheng Chen +1
Deep Reinforcement Learning (DRL) has gained prominence as an effective approach for control systems. However, its practical deployment is impeded by state perturbations that can s…
cs.LG2022
Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training
Jiaxu Tian, Dapeng Zhi, Si Liu +3
The intrinsic complexity of deep neural networks (DNNs) makes it challenging to verify not only the networks themselves but also the hosting DNN-controlled systems. Reachability an…