no code implementations • 20 Nov 2023 • Niyousha Rahimi, Mehran Mesbahi
This paper addresses the problem of designing a data-driven feedback controller for complex nonlinear dynamical systems in the presence of time-varying disturbances with unknown dynamics.
no code implementations • 16 Nov 2023 • Beniamino Pozzan, Giulia Michieletto, Mehran Mesbahi, Angelo Cenedese
Characterized by a cross-disciplinary nature, the bearing-based target localization task involves estimating the position of an entity of interest by a group of agents capable of collecting noisy bearing measurements.
no code implementations • 26 Oct 2022 • Shahriar Talebi, Amirhossein Taghvaei, Mehran Mesbahi
Specifically, building on the duality between synthesizing optimal control and estimation gains, the filter design problem is formalized as direct policy learning.
no code implementations • 10 Oct 2022 • Bin Hu, Kaiqing Zhang, Na Li, Mehran Mesbahi, Maryam Fazel, Tamer Başar
Gradient-based methods have been widely used for system design and optimization in diverse application domains.
no code implementations • 22 Sep 2022 • Lulu Pan, Haibin Shao, Yang Lu, Mehran Mesbahi, Dewei Li, Yugeng Xi
We show that the vector-valued PPAC problem can be solved via associated matrix-weighted networks with the higher-dimensional agent state.
no code implementations • 28 Aug 2022 • Lulu Pan, Haibin Shao, Mehran Mesbahi, Dewei Li, Yugeng Xi
Inspired by the observation that the link redundancy in a network may degrade its diffusion performance, a distributed data-driven neighbor selection framework is proposed to adaptively adjust the network structure for improving the diffusion performance of exogenous influence over the network.
no code implementations • 26 Jul 2021 • Haibin Shao, Lulu Pan, Mehran Mesbahi, Yugeng Xi, Dewei Li
For distributed implementation, a quantitative connection between entries of Laplacian eigenvectors and the "relative rate of change" in the state between neighboring agents is further established; this connection facilitates a distributed algorithm for each agent to identify "favorable" neighbors to interact with.
no code implementations • 20 Jul 2021 • Lulu Pan, Haibin Shao, Mehran Mesbahi, Dewei Li, Yugeng Xi
Second, if the underlying network switches amongst infinite number of networks, the matrix-weighted integral network is employed to provide sufficient conditions for cluster consensus and the quantitative characterization of the corresponding steady-state of the multi-agent system, using null space analysis of matrix-valued Laplacian related of integral network associated with the switching networks.
1 code implementation • 22 Mar 2021 • Siavash Alemzadeh, Shahriar Talebi, Mehran Mesbahi
Control of networked systems, comprised of interacting agents, is often achieved through modeling the underlying interactions.
no code implementations • 5 Feb 2021 • Yue Yu, Shahriar Talebi, Henk J. van Waarde, Ufuk Topcu, Mehran Mesbahi, Behçet Açıkmeşe
Willems' fundamental lemma asserts that all trajectories of a linear time-invariant system can be obtained from a finite number of measured ones, assuming that controllability and a persistency of excitation condition hold.
1 code implementation • 21 Jul 2020 • Siavash Alemzadeh, Ramin Moslemi, Ratnesh Sharma, Mehran Mesbahi
In this work, we study adaptive data-guided traffic planning and control using Reinforcement Learning (RL).
1 code implementation • 12 Jul 2020 • Siavash Alemzadeh, Hesam Talebiyan, Shahriar Talebi, Leonardo Duenas-Osorio, Mehran Mesbahi
From an optimization point of view, resource allocation is one of the cornerstones of research for addressing limiting factors commonly arising in applications such as power outages and traffic jams.
1 code implementation • 29 May 2020 • Shahriar Talebi, Siavash Alemzadeh, Niyousha Rahimi, Mehran Mesbahi
Learning, say through direct policy updates, often requires assumptions such as knowing a priori that the initial policy (gain) is stabilizing, or persistently exciting (PE) input-output data, is available.
no code implementations • ICML 2018 • Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi
Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an "end-to-end" approach, directly optimizing the performance metric of interest 3) they inherently allow for richly parameterized policies.
no code implementations • ICLR 2018 • Maryam Fazel, Rong Ge, Sham M. Kakade, Mehran Mesbahi
Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model; 2) they are an "end-to-end" approach, directly optimizing the performance metric of interest; 3) they inherently allow for richly parameterized policies.
no code implementations • 22 Dec 2014 • Saghar Hosseini, Airlie Chapman, Mehran Mesbahi
This paper presents a distributed optimization scheme over a network of agents in the presence of cost uncertainties and over switching communication topologies.