Back to search

Georgia Institute of Technology

Verification Of Adversarially Robust Reinforcement Learning Mechanisms In Autonomous Systems

Abstract

dc:description.abstract

Artificial Intelligence (AI) is an effective algorithm for satisfying both optimality and adaptability in autonomous control systems. However, the policy generated from the AI is black-box, and since the algorithm cannot be analyzed in advance, this motivates the performance measurement of the AI model with verification. The performance and safety of the Cyber-Physical System(CPS) are subject to cyberattacks that intend to fail the system in operation or to interrupt the system from learning by modulation of learning data. For the safety and reliability scheme, verifying the impact of attacks on the CPS with the learning system is critical. This thesis proposal focuses on proposing one verification framework of adversarially robust Reinforcement Learning (RL) policy using the software toolkit ‘VERIFAI’, providing robustness measures over adversarial attack perturbations. This allows an algorithm engineer would be equipped with an RL control model verification toolbox that may be used to evaluate the reliability of any given attack mitigation algorithm and the performance of nonlinear control algorithms over their objectives. For this specified work, we developed the attack mitigating RL on nonlinear dynamics by the interconnection of off-policy RL and on-off adversarially robust mechanisms. After that, we connected with the simulation and verification toolkit for testing both the verification framework and integrated algorithm. The simulation experiment of the whole verification process was performed with two different control problems, one is a cart-pole problem from OpenAI gym, and the other problem is the attitude control of Cessna 172 in X-plane 11. From the experiment, we analyzed how the attack-mitigating RL algorithm performed with gain varying specific adversary attacks, and evaluated the generated model performance over the changing environmental parameters.

Degree

thesis:*
Level thesis:degree_level
Masters
Department dc:contributor.department
Aerospace Engineering
Grantor dc:publisher
Georgia Institute of Technology
Year dc:date.issued
2022

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Seo, Taehwan
Advisor dc:contributor.advisor
  • Vamvoudakis, Kyriakos G.
Committee members dc:contributor.committeemember
  • Chen, Yongxin
  • Mavris, Dimitri N.

Subjects

dc:subject × 9

Rights

Language dc:language.iso
en_US

Identifiers

dc:identifier.*
Handle dc:identifier.uri
https://hdl.handle.net/1853/72977

Chain of custody

source
Harvested from
Georgia Tech
Base URL
repository.gatech.edu/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Seo, Taehwan. Verification Of Adversarially Robust Reinforcement Learning Mechanisms In Autonomous Systems. Masters thesis, Georgia Institute of Technology, 2022. https://hdl.handle.net/1853/72977