Search Results for author: Dapeng Zhi

Found 2 papers, 0 papers with code

Robustness Verification of Deep Reinforcement Learning Based Control Systems using Reward Martingales

no code implementations15 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.

Taming Reachability Analysis of DNN-Controlled Systems via Abstraction-Based Training

no code implementations21 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.

Decision Making Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.