Master Thesis Defense: Taehwan Seo

Wed Nov 30 2022 10:30 AM
Weber 200 or Virtual via Zoom

Taehwan Seo

(Advisor: Prof. Kyriakos G. Vamvoudakis)

"Verification of Adversarially Robust Reinforcement Learning Mechanisms in Autonomous Systems"

On

Wednesday, November 30

10:30 a.m.

Weber 200

https://gatech.zoom.us/j/99254350217?pwd=ZTlYek1zK2ZoaVZ4blJoOU1RTVJoQT09

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.

Committee

  • Prof. Kyriakos G. Vamvoudakis – School of Aerospace Engineering (advisor)
  • Prof. Dimitiri Mavris– School of Aerospace Engineering
  • Prof. Yongxin Chen – School of Aerospace Engineering