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

Towards a TEE-based V2V Protocol for Connected and Autonomous...

Mohit Kumar Jangid (Ohio State University) and Zhiqiang Lin (Ohio State University)

Read More

Demo #12: Too Afraid to Drive: Systematic Discovery of...

Ziwen Wan (UC Irvine), Junjie Shen (UC Irvine), Jalen Chuang (UC Irvine), Xin Xia (UCLA), Joshua Garcia (UC Irvine), Jiaqi Ma (UCLA) and Qi Alfred Chen (UC Irvine)

Read More

What Remains Uncaught?: Characterizing Sparsely Detected Malicious URLs on...

Sayak Saha Roy, Unique Karanjit, Shirin Nilizadeh (The University of Texas at Arlington)

Read More