no code implementations • 2 Apr 2024 • Dapeng Zhi, Peixin Wang, Si Liu, Luke Ong, Min Zhang
We also devise a simulation-guided approach for training NBCs, aiming to achieve tightness in computing precise certified lower and upper bounds.
no code implementations • 15 Dec 2023 • Dapeng Zhi, Peixin Wang, Cheng Chen, Min Zhang
In this work, we present the first approach for robustness verification of DRL-based control systems by introducing reward martingales, which offer a rigorous mathematical foundation to characterize the impact of state perturbations on system performance in terms of cumulative rewards.
no code implementations • 21 Nov 2022 • Jiaxu Tian, Dapeng Zhi, Si Liu, Peixin Wang, Guy Katz, Min Zhang
The experimental results on a wide range of benchmarks show that the DNNs trained by using our approach exhibit comparable performance, while the reachability analysis of the corresponding systems becomes more amenable with significant tightness and efficiency improvement over the state-of-the-art white-box approaches.