Environment poisoning in reinforcement learning: attacks and resilience

As Reinforcement Learning (RL) systems have been widely adopted in real-world applications, the security of these systems has become increasingly significant. Thus, it is essential to protect RL systems against a variety of adversarial attacks. Of these attacks, a training-time attack is considered...

Full description

Saved in:
Bibliographic Details
Main Author: Xu, Hang
Other Authors: Zinovi Rabinovich
Format: Thesis-Doctor of Philosophy
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/164969
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English