no code implementations • 29 Jul 2022 • Yixiang Wang, Yujing Hu, Feng Wu, Yingfeng Chen
In this paper, we propose to automatically generate goal-consistent intrinsic rewards for the agent to learn, by maximizing which the expected accumulative extrinsic rewards can be maximized.
no code implementations • 14 Oct 2021 • Yixiang Wang, Jiqiang Liu, Xiaolin Chang, Jianhua Wang, Ricardo J. Rodríguez
In this paper, we propose an interpretable white-box AE attack approach, DI-AA, which explores the application of the interpretable approach of the deep Taylor decomposition in the selection of the most contributing features and adopts the Lagrangian relaxation optimization of the logit output and L_p norm to further decrease the perturbation.
no code implementations • 3 Feb 2021 • Yixiang Wang, Jiqiang Liu, Xiaolin Chang, Jelena Mišić, Vojislav B. Mišić
To further make the perturbations more imperceptible, we propose to employ the restriction combination of $L_0$ and $L_1/L_2$ secondly, which can restrict the total perturbations and perturbation points simultaneously.
no code implementations • 25 Jan 2021 • Yixiang Wang, Jiqiang Liu, Xiaolin Chang
Recent research has proved that deep neural networks (DNNs) are vulnerable to adversarial examples, the legitimate input added with imperceptible and well-designed perturbations can fool DNNs easily in the testing stage.
no code implementations • NeurIPS 2020 • Yujing Hu, Weixun Wang, Hangtian Jia, Yixiang Wang, Yingfeng Chen, Jianye Hao, Feng Wu, Changjie Fan
In this paper, we consider the problem of adaptively utilizing a given shaping reward function.
no code implementations • 28 Nov 2019 • Yixiang Wang, Feng Wu
To tackle this, we propose to train multiple policies for each agent and postpone the selection of the best policy at execution time.
Multi-agent Reinforcement Learning reinforcement-learning +1