Yunzhe Tian, Yike Li, Yingxiao Xiang, Wenjia Niu, Endong Tong, and Jiqiang Liu (Beijing Jiaotong University)

Robust reinforcement learning has been a challenging problem due to always unknown differences between real and training environment. Existing efforts approached the problem through performing random environmental perturbations in learning process. However, one can not guarantee perturbation is positive. Bad ones might bring failures to reinforcement learning. Therefore, in this paper, we propose to utilize GAN to dynamically generate progressive perturbations at each epoch and realize curricular policy learning. Demo we implemented in unmanned CarRacing game validates the effectiveness.

View More Papers

CV-Inspector: Towards Automating Detection of Adblock Circumvention

Hieu Le (University of California, Irvine), Athina Markopoulou (University of California, Irvine), Zubair Shafiq (University of California, Davis)

Read More

Oblivious DNS over HTTPS (ODoH): A Practical Privacy Enhancement...

Sudheesh Singanamalla*†, Suphanat Chunhapanya*, Jonathan Hoyland*, Marek Vavruša*, Tanya Verma*, Peter Wu*, Marwan Fayed*, Kurtis Heimerl†, Nick Sullivan*, Christopher Wood* (*Cloudflare Inc. †University of Washington)

Read More

Processing Dangerous Paths – On Security and Privacy of...

Jens Müller (Ruhr University Bochum), Dominik Noss (Ruhr University Bochum), Christian Mainka (Ruhr University Bochum), Vladislav Mladenov (Ruhr University Bochum), Jörg Schwenk (Ruhr University Bochum)

Read More

Detecting Tor Bridge from Sampled Traffic in Backbone Networks

Hua Wu (School of Cyber Science & Engineering and Key Laboratory of Computer Network and Information Integration Southeast University, Ministry of Education, Jiangsu Nanjing, Purple Mountain Laboratories for Network and Communication Security (Nanjing, Jiangsu)), Shuyi Guo, Guang Cheng, Xiaoyan Hu (School of Cyber Science & Engineering and Key Laboratory of Computer Network and Information Integration…

Read More