An Exploration-Free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System
J. Gornet, Y. Mo, B. Sinopoli
IEEE Conference on Decision and Control (CDC), 2025
Publications
Reinforcement LearningControl TheoryBandit AlgorithmsDistributed AI SystemsHyperparameter Optimization
See also my Google Scholar.
Peer-Reviewed
Restless Bandits with Rewards Generated by a Linear Gaussian Dynamical System
J. Gornet, B. Sinopoli
Learning for Dynamics and Control (L4DC), 2024
Two Measure is Two Know: Calibration-Free Full Duplex Monitoring for Software Radio Platforms
J. Wang, J. Gornet, A. Orange, L. Stoller, G. Wong, J. Van der Merwe, S. K. Kasera, N. Patwari
IEEE Symposium on Dynamic Spectrum Access Networks (DySPAN), 2024
Stochastic Multi-Armed Bandits with Non-Stationary Rewards Generated by a Linear Dynamical System
J. Gornet, M. Hosseinzadeh, B. Sinopoli
IEEE Conference on Decision and Control (CDC), 2022
Under Review
HyperController: A Hyperparameter Controller for Fast and Stable Training of Reinforcement Learning Neural Networks
J. Gornet, Y. Kantaros, B. Sinopoli
IEEE Transactions on Control Systems Technology (TCST) – revision under review, 2025
A Control Theory Inspired Exploration Method for a Linear Bandit Driven by a Linear Gaussian Dynamical System
J. Gornet, Y. Mo, B. Sinopoli
IEEE Transactions on Automatic Control (TAC) – submitted, 2025
An Adaptive Method for Contextual Stochastic Multi-Armed Bandits with Rewards Generated by a Linear Dynamical System
J. Gornet, M. Hosseinzadeh, B. Sinopoli
Automatica – submitted, 2024
Preprints
Distinct Ground State and Activated State Modes of Spiking in Forebrain Neurons
D. Levenstein, J. Gornet, R. Huszár, G. Girardeau, A. Grosmark, A. Peyrache, Y. Senzai, B. O. Watson, K. Mizuseki, J. Rinzel, G. Buzsáki
bioRxiv, 2021
Simulating Extracted Connectomes
J. Gornet, L. Scheffer
bioRxiv, 2017
Last updated October 2025