no code implementations • 1 Apr 2024 • Christoforos Somarakis, Raman Goyal, Erfaun Noorani, Shantanu Rane
A state-feedback watermarking signal design for the detection of replay attacks in linear systems is proposed.
no code implementations • 15 Mar 2024 • Nhan-Khanh Le, Erfaun Noorani, Sandra Hirche, John Baras
We study time-robust path planning for synthesizing robots' trajectories that adhere to spatial-temporal specifications expressed in Signal Temporal Logic (STL).
no code implementations • 13 Mar 2024 • Rui Liu, Erfaun Noorani, Pratap Tokekar, John S. Baras
In this study, we conduct a thorough iteration complexity analysis for the risk-sensitive policy gradient method, focusing on the REINFORCE algorithm and employing the exponential utility function.
1 code implementation • 17 Oct 2023 • Dominik Baumann, Erfaun Noorani, James Price, Ole Peters, Colm Connaughton, Thomas B. Schön
The expected value is the average over the statistical ensemble of infinitely many trajectories.
no code implementations • 2 Oct 2023 • Armin Lederer, Erfaun Noorani, John S. Baras, Sandra Hirche
We propose a method for learning these value functions using common techniques from reinforcement learning and derive sufficient conditions for its success.
1 code implementation • 19 May 2023 • Faisal Hamman, Erfaun Noorani, Saumitra Mishra, Daniele Magazzeni, Sanghamitra Dutta
There is an emerging interest in generating robust counterfactual explanations that would remain valid if the model is updated or changed even slightly.
no code implementations • 18 Dec 2022 • Erfaun Noorani, Christos Mavridis, John Baras
While reinforcement learning has shown experimental success in a number of applications, it is known to be sensitive to noise and perturbations in the parameters of the system, leading to high variance in the total reward amongst different episodes in slightly different environments.
no code implementations • 13 Sep 2022 • Raman Goyal, Christoforos Somarakis, Erfaun Noorani, Shantanu Rane
This work discusses a novel framework for simultaneous synthesis of optimal watermarking signal and robust controllers in cyber-physical systems to minimize the loss in performance due to added watermarking signal and to maximize the detection rate of the attack.
no code implementations • 27 Mar 2020 • Erfaun Noorani, Yagiz Savas, Alec Koppel, John Baras, Ufuk Topcu, Brian M. Sadler
In particular, we formulate a discrete optimization problem to choose only a subset of agents to transmit the message signal so that the variance of the signal-to-noise ratio (SNR) received by the base station is minimized while the expected SNR exceeds a desired threshold.