Search Results for author: Zhilu Wang

Found 9 papers, 3 papers with code

Collaborative Multi-Agent Video Fast-Forwarding

no code implementations27 May 2023 Shuyue Lan, Zhilu Wang, Ermin Wei, Amit K. Roy-Chowdhury, Qi Zhu

We show that compared with other approaches in the literature, our frameworks achieve better coverage of important frames, while significantly reducing the number of frames processed at each agent.

POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems

1 code implementation31 Mar 2023 YiXuan Wang, Weichao Zhou, Jiameng Fan, Zhilu Wang, Jiajun Li, Xin Chen, Chao Huang, Wenchao Li, Qi Zhu

We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions.

Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments

no code implementations29 Sep 2022 YiXuan Wang, Simon Sinong Zhan, Ruochen Jiao, Zhilu Wang, Wanxin Jin, Zhuoran Yang, Zhaoran Wang, Chao Huang, Qi Zhu

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 not to reach certain specified unsafe regions.

Reinforcement Learning (RL) Safe Reinforcement Learning

A Tool for Neural Network Global Robustness Certification and Training

no code implementations15 Aug 2022 Zhilu Wang, YiXuan Wang, Feisi Fu, Ruochen Jiao, Chao Huang, Wenchao Li, Qi Zhu

Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.

Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding

no code implementations26 Mar 2022 Zhilu Wang, Chao Huang, Qi Zhu

The robustness of deep neural networks has received significant interest recently, especially when being deployed in safety-critical systems, as it is important to analyze how sensitive the model output is under input perturbations.

Joint Differentiable Optimization and Verification for Certified Reinforcement Learning

no code implementations28 Jan 2022 YiXuan Wang, Simon Zhan, Zhilu Wang, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e. g., safety, stability) under the learned controller.

Bilevel Optimization Model-based Reinforcement Learning +2

POLAR: A Polynomial Arithmetic Framework for Verifying Neural-Network Controlled Systems

2 code implementations25 Jun 2021 Chao Huang, Jiameng Fan, Zhilu Wang, YiXuan Wang, Weichao Zhou, Jiajun Li, Xin Chen, Wenchao Li, Qi Zhu

We present POLAR, a polynomial arithmetic-based framework for efficient bounded-time reachability analysis of neural-network controlled systems (NNCSs).

Verification in the Loop: Correct-by-Construction Control Learning with Reach-avoid Guarantees

no code implementations6 Jun 2021 YiXuan Wang, Chao Huang, Zhaoran Wang, Zhilu Wang, Qi Zhu

Specifically, we leverage the verification results (computed reachable set of the system state) to construct feedback metrics for control learning, which measure how likely the current design of control parameters can meet the required reach-avoid property for safety and goal-reaching.

Distributed Multi-agent Video Fast-forwarding

1 code implementation10 Aug 2020 Shuyue Lan, Zhilu Wang, Amit K. Roy-Chowdhury, Ermin Wei, Qi Zhu

In many intelligent systems, a network of agents collaboratively perceives the environment for better and more efficient situation awareness.

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