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

DOVE: A Data-Oblivious Virtual Environment

Hyun Bin Lee (University of Illinois at Urbana-Champaign), Tushar M. Jois (Johns Hopkins University), Christopher W. Fletcher (University of Illinois at Urbana-Champaign), Carl A. Gunter (University of Illinois at Urbana-Champaign)

Read More

Awakening the Web's Sleeper Agents: Misusing Service Workers for...

Soroush Karami (University of Illinois at Chicago), Panagiotis Ilia (University of Illinois at Chicago), Jason Polakis (University of Illinois at Chicago)

Read More

(Short) Spoofing Mobileye 630’s Video Camera Using a Projector

Ben Nassi, Dudi Nassi, Raz Ben Netanel and Yuval Elovici (Ben-Gurion University of the Negev)

Read More

Demo #15: Remote Adversarial Attack on Automated Lane Centering

Yulong Cao (University of Michigan), Yanan Guo (University of Pittsburgh), Takami Sato (UC Irvine), Qi Alfred Chen (UC Irvine), Z. Morley Mao (University of Michigan) and Yueqiang Cheng (NIO)

Read More