Kyriakos G. Vamvoudakis
Georgia Institute of Technology
216 Papers
305 Citations
Kyriakos G. Vamvoudakis is an academic researcher from Georgia Institute of Technology. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 27, co-authored 153 publications. Previous affiliations of Kyriakos G. Vamvoudakis include University of California & University of Texas System.
Chat about Author
Papers
Online Learning-based Optimal Control of Nonlinear Systems with Finite-Time Convergence Guarantees
Nick-Marios T. Kokolakis,Kyriakos G. Vamvoudakis +1 more
- 08 Jun 2022
TL;DR: A critic-only reinforcement learning-based algorithm for learning the solution to the Hamilton-Jacobi-Bellman equation in finite time using a non-Lipschitz experience replay-based learning law utilizing recorded and current data for updating the critic weights to learn the value function.
5
Optimal Recursive Backstepping for Nonlinear Systems in a Strict-Feedback Form with Continuous and Intermittent Updates
Yongliang Yang,Hamidreza Modares,Kyriakos G. Vamvoudakis,Cheng-Zhong Xu +3 more
- 14 Dec 2020
TL;DR: In this paper, an optimal recursive back-stepping design for the optimal regulation of a class of nonlinear systems in a strict-feedback form is presented, which results in the asymptotic stability of the equilibrium point for isolated systems and ultimate boundedness for the cascade systems.
4
Detection of actuator faults for continuous-time systems with intermittent state feedback
TL;DR: In this article, the authors consider the problem of detecting actuator faults on uncertain continuous-time systems, where the state can be measured only intermittently, and derive a necessary and sufficient condition, the verification of which allows us to detect the aforementioned inconsistencies.
4
Attack Identification for Cyber-Physical Security in Dynamic Games under Cognitive Hierarchy
Christos N. Mavridis,Aris Kanellopoulos,Kyriakos G. Vamvoudakis,John S. Baras,K. E. Johansson +4 more
TL;DR: In this article , the authors considered the problem of identifying the profiles and capabilities of attackers injecting adversarial inputs to a cyber-physical system and used behavioral game theory to construct a database of potential attack vectors.
4
A Meta-Learning and Bounded Rationality Framework for Repeated Games in Adversarial Environments
Aris Kanellopoulos,Filippos Fotiadis,Kyriakos G. Vamvoudakis,Vijay Gupta +3 more
- 14 Dec 2020
TL;DR: In this paper, a meta-learning framework for games between adapting players is proposed, where an agent with increased cognitive abilities is augmented with a structure that allows them to identify the way that their opponents learn during the game.
4