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 Defeating Mass Surveillance and SARS-CoV-2: The Pronto-C2 Fully...

Gennaro Avitabile, Vincenzo Botta, Vincenzo Iovino, and Ivan Visconti (University of Salerno)

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

Detecting CAN Masquerade Attacks with Signal Clustering Similarity

Pablo Moriano (Oak Ridge National Laboratory), Robert A. Bridges (Oak Ridge National Laboratory) and Michael D. Iannacone (Oak Ridge National...

Read More

“Lose Your Phone, Lose Your Identity”: Exploring Users’ Perceptions...

Michael Lutaaya, Hala Assal, Khadija Baig, Sana Maqsood, Sonia Chiasson (Carleton University)

Read More