Adversarial robustness of deep reinforcement learning

Over the past decades, the advancements in deep reinforcement learning (DRL) have demonstrated that deep neural network (DNN) policies can be trained to prescribe near-optimal actions in many complex tasks. Unfortunately, DNN policies are shown to be vulnerable to adversarial perturbations in the in...

Full description

Saved in:
Bibliographic Details
Main Author: Qu, Xinghua
Other Authors: Ong Yew Soon
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/154587
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English