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

Deceptive Deletions for Protecting Withdrawn Posts on Social Media...

Mohsen Minaei (Visa Research), S Chandra Mouli (Purdue University), Mainack Mondal (IIT Kharagpur), Bruno Ribeiro (Purdue University), Aniket Kate (Purdue University)

Read More

VISAS-Detecting GPS spoofing attacks against drones by analyzing camera's...

Barak Davidovich (Ben-Gurion University of the Negev), Ben Nassi (Ben-Gurion University of the Negev) and Yuval Elovici (Ben-Gurion University of the Negev)

Read More

PFirewall: Semantics-Aware Customizable Data Flow Control for Smart Home...

Haotian Chi (Temple University), Qiang Zeng (University of South Carolina), Xiaojiang Du (Temple University), Lannan Luo (University of South Carolina)

Read More

Demo #8: Identifying Drones Based on Visual Tokens

Ben Nassi (Ben-Gurion University of the Negev), Elad Feldman (Ben-Gurion University of the Negev), Aviel Levy (Ben-Gurion University of the Negev), Yaron Pirutin (Ben-Gurion University of the Negev), Asaf Shabtai (Ben-Gurion University of the Negev), Ryusuke Masuoka (Fujitsu System Integration Laboratories) and Yuval Elovici (Ben-Gurion University of the Negev)

Read More