papers

Publications (12)

eess.SY2024

Improving a Proportional Integral Controller with Reinforcement Learning on a Throttle Valve Benchmark

Paul Daoudi, Bojan Mavkov, Bogdan Robu +4

This paper presents a learning-based control strategy for non-linear throttle valves with an asymmetric hysteresis, leading to a near-optimal controller without requiring any prior…

cs.LG2024

A Conservative Approach for Few-Shot Transfer in Off-Dynamics Reinforcement Learning

Paul Daoudi, Christophe Prieur, Bogdan Robu +2

Off-dynamics Reinforcement Learning (ODRL) seeks to transfer a policy from a source environment to a target environment characterized by distinct yet similar dynamics. In this cont…

cs.LG2019

Feedback Control for Online Training of Neural Networks

Zilong Zhao, Sophie Cerf, Bogdan Robu +1

Convolutional neural networks (CNNs) are commonly used for image classification tasks, raising the challenge of their application on data flows. During their training, adaptation i…

eess.SY2023

Sparse Dynamical Features generation, application to Parkinson's Disease diagnosis

Houssem Meghnoudj, Bogdan Robu, Mazen Alamir

In this study we focus on the diagnosis of Parkinson's Disease (PD) based on electroencephalogram (EEG) signals. We propose a new approach inspired by the functioning of the brain…

cs.LG2019

RAD: On-line Anomaly Detection for Highly Unreliable Data

Zilong Zhao, Robert Birke, Rui Han +4

Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source…

cs.DC2026

LPV Control for Dynamic Power Capping in High-Performance Computing under Mixed Workloads

Mohamed Abdeldjalil Maziz, Kouds Halitim, Bogdan Robu +1

Balancing energy consumption and performance remains a critical challenge in High Performance Computing (HPC) systems. While static power capping mechanisms such as Intel's Running…

cs.DC2025

Mitigating Shared Storage Congestion Using Control Theory

Thomas Collignon, Kouds Halitim, Raphaël Bleuse +5

Efficient data access in High-Performance Computing (HPC) systems is essential to the performance of intensive computing tasks. Traditional optimizations of the I/O stack aim to im…

cs.LG2020

Event-Based Control for Online Training of Neural Networks

Zilong Zhao, Sophie Cerf, Bogdan Robu +1

Convolutional Neural Network (CNN) has become the most used method for image classification tasks. During its training the learning rate and the gradient are two key factors to tun…

quant-ph2017

Nanobob: A Cubesat Mission Concept For Quantum Communication Experiments In An Uplink Configuration

Erik Kerstel, Arnaud Gardelein, Mathieu Barthelemy +23

We present a ground-to-space quantum key distribution (QKD) mission concept and the accompanying feasibility study for the development of the low earth orbit CubeSat payload. The q…

cs.LG2024

Enhancing Reinforcement Learning Agents with Local Guides

Paul Daoudi, Bogdan Robu, Christophe Prieur +2

This paper addresses the problem of integrating local guide policies into a Reinforcement Learning agent. For this, we show how to adapt existing algorithms to this setting before…

cs.LG2026

A Unified Representation of Neural Networks Architectures

Christophe Prieur, Mircea Lazar, Bogdan Robu

In this paper we consider the limiting case of neural networks (NNs) architectures when the number of neurons in each hidden layer and the number of hidden layers tend to infinity…

cs.LG2021

Enhancing Robustness of On-line Learning Models on Highly Noisy Data

Zilong Zhao, Robert Birke, Rui Han +4

Classification algorithms have been widely adopted to detect anomalies for various systems, e.g., IoT, cloud and face recognition, under the common assumption that the data source…