1 code implementation • 26 Mar 2024 • Ehsan Sabouni, H. M. Sabbir Ahmad, Vittorio Giammarino, Christos G. Cassandras, Ioannis Ch. Paschalidis, Wenchao Li
Unfortunately, both performance and solution feasibility can be significantly impacted by two key factors: (i) the selection of the cost function and associated parameters, and (ii) the calibration of parameters within the CBF-based constraints, which capture the trade-off between performance and conservativeness.
no code implementations • 27 Feb 2024 • Zijian Guo, Weichao Zhou, Wenchao Li
Offline safe reinforcement learning (RL) aims to train a constraint satisfaction policy from a fixed dataset.
1 code implementation • 17 Jan 2024 • Aida Afshar, Wenchao Li
Reinforcement learning (RL) offers a capable and intuitive structure for the fundamental sequential decision-making problem.
1 code implementation • 4 Jan 2024 • H M Sabbir Ahmad, Ehsan Sabouni, Akua Dickson, Wei Xiao, Christos G. Cassandras, Wenchao Li
We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to safely navigate through a conflict area (e. g., traffic intersections, merging roadways, roundabouts).
1 code implementation • 6 Nov 2023 • Wenchao Li, Bangshu Xiong, Qiaofeng Ou, Xiaoyun Long, Jinhao Zhu, Jiabao Chen, Shuyuan Wen
Two difficulties here make low-light image enhancement a challenging task; firstly, it needs to consider not only luminance restoration but also image contrast, image denoising and color distortion issues simultaneously.
no code implementations • 15 Jun 2023 • Feisi Fu, Wenchao Li
Existing ownership verification methods either modify or introduce constraints to the neural network parameters, which are accessible to an attacker in a white-box attack and can be harmful to the network's normal operation, or train the network to respond to specific watermarks in the inputs similar to data poisoning-based backdoor attacks, which are susceptible to backdoor removal techniques.
no code implementations • 2 Jun 2023 • Weichao Zhou, Wenchao Li
Many imitation learning (IL) algorithms employ inverse reinforcement learning (IRL) to infer the intrinsic reward function that an expert is implicitly optimizing for based on their demonstrated behaviors.
1 code implementation • 26 May 2023 • H M Sabbir Ahmad, Ehsan Sabouni, Wei Xiao, Christos G. Cassandras, Wenchao Li
We address the security of a network of Connected and Automated Vehicles (CAVs) cooperating to navigate through a conflict area.
no code implementations • 26 May 2023 • Ehsan Sabouni, H. M. Sabbir Ahmad, Christos G. Cassandras, Wenchao Li
We address the problem of merging traffic from two roadways consisting of both Connected Autonomous Vehicles (CAVs) and Human Driven Vehicles (HDVs).
1 code implementation • 31 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.
no code implementations • 3 Mar 2023 • James Brotchie, Wenchao Li, Andrew D. Greentree, Allison Kealy
Our approach, which incorporates the true position priors in the training process, is trained on inertial measurements and ground truth displacement data, allowing recursion and to learn both motion characteristics and systemic error bias and drift.
no code implementations • 2 Nov 2022 • Feisi Fu, Panagiota Kiourti, Wenchao Li
We present a novel methodology for neural network backdoor attacks.
no code implementations • 15 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.
no code implementations • 20 Apr 2022 • Weichao Zhou, Wenchao Li
A misspecified reward can degrade sample efficiency and induce undesired behaviors in reinforcement learning (RL) problems.
no code implementations • 14 Dec 2021 • Weichao Zhou, Wenchao Li
In this paper, we propose the idea of programmatic reward design, i. e. using programs to specify the reward functions in RL environments.
2 code implementations • ICLR 2022 • Feisi Fu, Wenchao Li
By leveraging the piecewise linear nature of ReLU networks, our approach can efficiently construct a patch network tailored to the linear region where the buggy input resides, which when combined with the original network, provably corrects the behavior on the buggy input.
2 code implementations • 25 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).
no code implementations • 29 Mar 2021 • Panagiota Kiourti, Wenchao Li, Anirban Roy, Karan Sikka, Susmit Jha
Recent studies have shown that neural networks are vulnerable to Trojan attacks, where a network is trained to respond to specially crafted trigger patterns in the inputs in specific and potentially malicious ways.
1 code implementation • 26 Feb 2021 • Jiameng Fan, Wenchao Li
This approach enables us to train high-performance policies that are robust to visual distractions and can generalize well to unseen environments.
no code implementations • 17 Aug 2020 • Weichao Zhou, Ruihan Gao, BaekGyu Kim, Eunsuk Kang, Wenchao Li
The key idea behind our approach is the formulation of a trajectory optimization problem that allows the joint reasoning of policy update and safety constraints.
1 code implementation • 13 Aug 2020 • Jiameng Fan, Wenchao Li
We propose a principled framework that combines adversarial training and provable robustness verification for training certifiably robust neural networks.
1 code implementation • 25 Jun 2019 • Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen, Qi Zhu
In this work, we propose a new reachability analysis approach based on Bernstein polynomials that can verify neural-network controlled systems with a more general form of activation functions, i. e., as long as they ensure that the neural networks are Lipschitz continuous.
no code implementations • 6 Mar 2019 • Jiameng Fan, Wenchao Li
An important facet of reinforcement learning (RL) has to do with how the agent goes about exploring the environment.
2 code implementations • 1 Mar 2019 • Panagiota Kiourti, Kacper Wardega, Susmit Jha, Wenchao Li
Recent work has identified that classification models implemented as neural networks are vulnerable to data-poisoning and Trojan attacks at training time.
1 code implementation • 22 Oct 2017 • Weichao Zhou, Wenchao Li
Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and the agent has to derive a good policy by observing an expert's demonstrations.
no code implementations • 13 Mar 2014 • Shalini Ghosh, Daniel Elenius, Wenchao Li, Patrick Lincoln, Natarajan Shankar, Wilfried Steiner
Requirements are informal and semi-formal descriptions of the expected behavior of a complex system from the viewpoints of its stakeholders (customers, users, operators, designers, and engineers).