arXiv subjects

Chaouki Abdallah

Publications and source records attributed to Chaouki Abdallah.

9 recordsLinked to original sources

arXiv2026

Graph Feedback Controls Consensus and Clique Formation in Open-Weight Language-Model Populations

Multi-agent language-model (LM) systems often determine which agents communicate, yet routing is usually treated as an implementation detail. We ask whether routing itself determines whether a population converges on a shared convention or fragments into persistent cliques. We study open-weight agents spanning 1.1B-32B parameters in a controlled naming game, tracking both emitted labels and full first-token preference distributions over the allowed labels. Similarity-based routing can isolate emerging conventions and sustain fragmentation even when every agent interacts in every round. Matched controls show that this effect is not explained solely by uneven participation or model-family-specific score preferences: random rematching and policies that connect disagreeing groups improve coordination when partner-label history is retained, but not when it is absent. Exposure alone is nevertheless insufficient, as some mixed-model populations remain divided despite frequent cross-family interaction, although the same models coordinate homogeneously. Trajectory and controlled-history analyses further distinguish reaching consensus from maintaining it. Finally, ARC-Challenge and MMLU experiments show that routing changes how correct and incorrect answers propagate without reliably improving accuracy. These results establish the runtime interaction graph as a causal design variable whose effects depend jointly on memory, model response, and population composition.

cs.AI↗

arXiv2024

Finite Horizon Multi-Agent Reinforcement Learning in Solving Optimal Control of State-Dependent Switched Systems

In this article, a \underline{S}tate-dependent \underline{M}ulti-\underline{A}gent \underline{D}eep \underline{D}eterministic \underline{P}olicy \underline{G}radient (\textbf{SMADDPG}) method is proposed in order to learn an optimal control policy for regionally switched systems. We observe good performance of this method and explain it in a rigorous mathematical language using some simplifying assumptions in order to motivate the ideas and to apply them to some canonical examples. Using reinforcement learning, the performance of the switched learning-based multi-agent method is compared with the vanilla DDPG in two customized demonstrative environments with one and two-dimensional state spaces.

eess.SY↗

arXiv2024

A Model-Free Optimal Control Method With Fixed Terminal States and Delay

Model-free algorithms are brought into the control system's research with the emergence of reinforcement learning algorithms. However, there are two practical challenges of reinforcement learning-based methods. First, learning by interacting with the environment is highly complex. Second, constraints on the states (boundary conditions) require additional care since the state trajectory is implicitly defined from the inputs and system dynamics. To address these problems, this paper proposes a new model-free algorithm based on basis functions, gradient estimation, and the Lagrange method. The favorable performance of the proposed algorithm is shown using several examples under state-dependent switches and time delays.

eess.SY↗

arXiv2023

Consensus controller with safety guarantee: an application to the kinematic bicycle model

This paper proposes a consensus controller for multi-agent systems that can guarantee the agents' safety. The controller, built with the idea of output prediction and the Newton-Raphson method, achieves consensus for a class of heterogeneous nonlinear systems. The Integral Control Barrier Function is applied in conjunction with the controller, such that the agents' states are confined within pre-defined safety sets. Due to the dynamically-defined control input, the resulting optimization problem from the barrier function is always a Quadratic Program, despite the nonlinearities that the system dynamics may have. We verify the proposed controller using a platoon of autonomous vehicles modeled by kinematic bicycles. A convergence analysis of the leader-follower consensus under the path graph topology is conducted. Simulation results show that the vehicles achieve consensus while keeping safe inter-agent distances, suggesting a potential in future applications.

eess.SY↗

arXiv2023

Energy Optimal Control of a Harmonic Oscillator with a State Inequality Constraint

In this article, the optimal control problem for a harmonic oscillator with an inequality constraint is considered. The applied energy of the oscillator during a fixed final time period is used as the performance criterion. The analytical solution with both small and large terminal time is found for a special case when the undriven oscillator system is initially at rest. For other initial states of the Harmonic oscillator, the optimal solution is found to have three modes: wait-move, move-wait, and move-wait-move given a longer terminal time.

eess.SY↗

arXiv2022

Jump Law of Co-State in Optimal Control for State-Dependent Switched Systems and Applications

This paper presents the jump law of co-states in optimal control for state-dependent switched systems. The number of switches and the switching modes are assumed to be known a priori. A proposed jump law is rigorously derived by theoretical analysis and illustrated by simulation results. An algorithm is then proposed to solve optimal control for state-dependent hybrid systems. Through numerical simulations, we further show that the proposed approach is more efficient than existing methods in solving optimal control for state-dependent switched systems.

math.OC↗

arXiv2021

The Effect of Training Parameters and Mechanisms on Decentralized Federated Learning based on MNIST Dataset

Federated Learning is an algorithm suited for training models on decentralized data, but the requirement of a central "server" node is a bottleneck. In this document, we first introduce the notion of Decentralized Federated Learning (DFL). We then perform various experiments on different setups, such as changing model aggregation frequency, switching from independent and identically distributed (IID) dataset partitioning to non-IID partitioning with partial global sharing, using different optimization methods across clients, and breaking models into segments with partial sharing. All experiments are run on the MNIST handwritten digits dataset. We observe that those altered training procedures are generally robust, albeit non-optimal. We also observe failures in training when the variance between model weights is too large. The open-source experiment code is accessible through GitHub\footnote{Code was uploaded at \url{https://github.com/zhzhang2018/DecentralizedFL}}.

cs.LG↗

arXiv2006

A Mobile Transient Internet Architecture

This paper describes a new architecture for transient mobile networks destined to merge existing and future network architectures, communication implementations and protocol operations by introducing a new paradigm to data delivery and identification. The main goal of our research is to enable seamless end-to-end communication between mobile and stationary devices across multiple networks and through multiple communication environments. The architecture establishes a set of infrastructure components and protocols that set the ground for a Persistent Identification Network (PIN). The basis for the operation of PIN is an identification space consisting of unique location independent identifiers similar to the ones implemented in the Handle system. Persistent Identifiers are used to identify and locate Digital Entities which can include devices, services, users and even traffic. The architecture establishes a primary connection independent logical structure that can operate over conventional networks or more advanced peer-to-peer aggregation networks. Communication is based on routing pools and novel protocols for routing data across several abstraction levels of the network, regardless of the end-points' current association and state...

cs.NI↗

arXiv2006

An Application of the Mobile Transient Internet Architecture to IP Mobility and Inter-Operability

We introduce an application of a mobile transient network architecture on top of the current Internet. This paper is an application extension to a conceptual mobile network architecture. It attempts to specifically reinforce some of the powerful notions exposed by the architecture from an application perspective. Of these notions, we explore the network expansion layer, an overlay of components and services, that enables a persistent identification network and other required services. The overlay abstraction introduces several benefits of which mobility and communication across heterogenous network structures are of interest to this paper. We present implementations of several components and protocols including gateways, Agents and the Open Device Access Protocol. Our present identification network implementation exploits the current implementation of the Handle System through the use of distributed, global and persistent identifiers called handles. Handles are used to identify and locate devices and services abstracting any physical location or network association from the communicating ends. A communication framework is finally demonstrated that would allow for mobile devices on the public Internet to have persistent identifiers and thus be persistently accessible either directly or indirectly. This application expands IP inter-operability beyond its current boundaries.

cs.NI↗