no code implementations • 16 Apr 2024 • Hao-Lun Hsu, Weixin Wang, Miroslav Pajic, Pan Xu
This is the first theoretical result for randomized exploration in cooperative MARL.
no code implementations • 7 Apr 2024 • Zetong Xuan, Alper Kamil Bozkurt, Miroslav Pajic, Yu Wang
In a widely-adopted surrogate reward approach, two discount factors are used to ensure that the expected return approximates the satisfaction probability of the LTL objective.
no code implementations • 11 Mar 2024 • Hao-Lun Hsu, Qitong Gao, Miroslav Pajic
Traditional commercial DBS devices are only able to deliver fixed-frequency periodic pulses to the basal ganglia (BG) regions of the brain, i. e., continuous DBS (cDBS).
no code implementations • 10 Dec 2023 • Muhammad Abdullah Naeem, Miroslav Pajic
Performance of ordinary least squares(OLS) method for the \emph{estimation of high dimensional stable state transition matrix} $A$(i. e., spectral radius $\rho(A)<1$) from a single noisy observed trajectory of the linear time invariant(LTI)\footnote{Linear Gaussian (LG) in Markov chain literature} system $X_{-}:(x_0, x_1, \ldots, x_{N-1})$ satisfying \begin{equation} x_{t+1}=Ax_{t}+w_{t}, \hspace{10pt} \text{ where } w_{t} \thicksim N(0, I_{n}), \end{equation} heavily rely on negative moments of the sample covariance matrix: $(X_{-}X_{-}^{*})=\sum_{i=0}^{N-1}x_{i}x_{i}^{*}$ and singular values of $EX_{-}^{*}$, where $E$ is a rectangular Gaussian ensemble $E=[w_0, \ldots, w_{N-1}]$.
no code implementations • 27 Nov 2023 • David Hunt, Kristen Angell, Zhenzhou Qi, Tingjun Chen, Miroslav Pajic
Frequency modulated continuous wave (FMCW) millimeter-wave (mmWave) radars play a critical role in many of the advanced driver assistance systems (ADAS) featured on today's vehicles.
no code implementations • 16 Oct 2023 • Muhammad Abdullah Naeem, Amir Khazraei, Miroslav Pajic
In the light of these findings we set the stage for non-asymptotic error analysis in estimation of state transition matrix $A$ via least squares regression on observed trajectory by showing that element-wise error is essentially a variant of well-know Littlewood-Offord problem.
no code implementations • 6 Oct 2023 • Amir Khazraei, Miroslav Pajic
When the attacker has complete knowledge about the system, we show that if the closed loop system is incrementally exponentially stable while the open loop plant is incrementally unstable, then the system is vulnerable to stealthy yet impactful attacks on sensors.
no code implementations • 20 Jun 2023 • Ahmed Aloui, Ali Hasan, Yuting Ng, Miroslav Pajic, Vahid Tarokh
Understanding individual treatment effects in extreme regimes is important for characterizing risks associated with different interventions.
no code implementations • 12 Jun 2023 • Juncheng Dong, Hao-Lun Hsu, Qitong Gao, Vahid Tarokh, Miroslav Pajic
In this work, we extend the two-player game by introducing an adversarial herd, which involves a group of adversaries, in order to address ($\textit{i}$) the difficulty of the inner optimization problem, and ($\textit{ii}$) the potential over pessimism caused by the selection of a candidate adversary set that may include unlikely scenarios.
1 code implementation • 13 Mar 2023 • R. Spencer Hallyburton, Nate Zelter, David Hunt, Kristen Angell, Miroslav Pajic
Leading autonomous vehicle (AV) platforms and testing infrastructures are, unfortunately, proprietary and closed-source.
1 code implementation • 5 Feb 2023 • Qitong Gao, Stephen L. Schimdt, Afsana Chowdhury, Guangyu Feng, Jennifer J. Peters, Katherine Genty, Warren M. Grill, Dennis A. Turner, Miroslav Pajic
In this work, we introduce an offline reinforcement learning (RL) framework, allowing the use of past clinical data to train an RL policy to adjust the stimulation amplitude in real time, with the goal of reducing energy use while maintaining the same level of treatment (i. e., control) efficacy as cDBS.
1 code implementation • 28 Jan 2023 • Qitong Gao, Ge Gao, Min Chi, Miroslav Pajic
In this work, we propose the variational latent branching model (VLBM) to learn the transition function of MDPs by formulating the environmental dynamics as a compact latent space, from which the next states and rewards are then sampled.
no code implementations • 7 Dec 2022 • Muhammad Abdullah Naeem, Miroslav Pajic
Via operator theoretic methods, we formalize the concentration phenomenon for a given observable `$r$' of a discrete time Markov chain with `$\mu_{\pi}$' as invariant ergodic measure, possibly having support on an unbounded state space.
no code implementations • 14 Jun 2022 • Amir Khazraei, Henry Pfister, Miroslav Pajic
Specifically, we consider a general setup with a nonlinear affine physical plant controlled with a perception-based controller that maps both the physical (e. g., IMUs) and perceptual (e. g., camera) sensing to the control input; the system is also equipped with a statistical or learning-based anomaly detector (AD).
no code implementations • 25 May 2022 • Muhammad Abdullah Naeem, Miroslav Pajic
We study the concentration phenomenon for discrete-time random dynamical systems with an unbounded state space.
1 code implementation • ICLR 2022 • Qitong Gao, Dong Wang, Joshua D. Amason, Siyang Yuan, Chenyang Tao, Ricardo Henao, Majda Hadziahmetovic, Lawrence Carin, Miroslav Pajic
Though recent works have developed methods that can generate estimates (or imputations) of the missing entries in a dataset to facilitate downstream analysis, most depend on assumptions that may not align with real-world applications and could suffer from poor performance in subsequent tasks such as classification.
no code implementations • 13 Jun 2021 • R. Spencer Hallyburton, Yupei Liu, Yulong Cao, Z. Morley Mao, Miroslav Pajic
Thus, in this work, we perform an analysis of camera-LiDAR fusion, in the AV context, under LiDAR spoofing attacks.
no code implementations • 26 Mar 2021 • Alper Kamil Bozkurt, Yu Wang, Miroslav Pajic
We study the problem of learning safe control policies that are also effective; i. e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance.
no code implementations • 10 Mar 2021 • Amir Khazraei, Spencer Hallyburton, Qitong Gao, Yu Wang, Miroslav Pajic
This work focuses on the use of deep learning for vulnerability analysis of cyber-physical systems (CPS).
no code implementations • 8 Mar 2021 • Shiqi Sun, Yan Zhang, Xusheng Luo, Panagiotis Vlantis, Miroslav Pajic, Michael M. Zavlanos
Using this abstraction, we propose a method to compute tight bounds on the safety probabilities of nodes in this graph, despite possible over-approximations of the transition probabilities between these nodes.
no code implementations • 8 Feb 2021 • Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos, Miroslav Pajic
By deriving distinct rewards and discount factors from the acceptance condition of the DPA, we reduce the maximization of the worst-case probability of satisfying the LTL specification into the maximization of a discounted reward objective in the product game; this enables the use of model-free RL algorithms to learn an optimal controller strategy.
no code implementations • 3 Aug 2020 • Yu Wang, Mojtaba Zarei, Borzoo Bonakdarpoor, Miroslav Pajic
In system analysis, conformance indicates that two systems simultaneously satisfy the same set of specifications of interest; thus, the results from analyzing one system automatically transfer to the other, or one system can safely replace the other in practice.
no code implementations • 15 Jun 2020 • Muhammad Abdullah Naeem, Miroslav Pajic
In this work, we show existence of invariant ergodic measure for switched linear dynamical systems (SLDSs) under a norm-stability assumption of system dynamics in some unbounded subset of $\mathbb{R}^{n}$.
no code implementations • 11 Jun 2020 • Yu Wang, Qitong Gao, Miroslav Pajic
For monotonicity constraints, we propose to use nonnegative neural networks and batch normalization.
2 code implementations • 16 Sep 2019 • Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos, Miroslav Pajic
We present a reinforcement learning (RL) framework to synthesize a control policy from a given linear temporal logic (LTL) specification in an unknown stochastic environment that can be modeled as a Markov Decision Process (MDP).