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

Differentially Private Health Tokens for Estimating COVID-19 Risk

David Butler, Chris Hicks, James Bell, Carsten Maple, and Jon Crowcroft (The Alan Turing Institute)

Read More

XDA: Accurate, Robust Disassembly with Transfer Learning

Kexin Pei (Columbia University), Jonas Guan (University of Toronto), David Williams-King (Columbia University), Junfeng Yang (Columbia University), Suman Jana (Columbia...

Read More

Manipulating the Byzantine: Optimizing Model Poisoning Attacks and Defenses...

Virat Shejwalkar (UMass Amherst), Amir Houmansadr (UMass Amherst)

Read More

Hunting the Haunter — Efficient Relational Symbolic Execution for...

Lesly-Ann Daniel (CEA, List, France), Sébastien Bardin (CEA, List, France), Tamara Rezk (Inria, France)

Read More