Second-Order MPC-Based Distributed Q-Learning

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mallick, Samuel, Airaldi, Filippo, Dabiri, Azita, De Schutter, Bart
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911651012280320
author Mallick, Samuel
Airaldi, Filippo
Dabiri, Azita
De Schutter, Bart
author_facet Mallick, Samuel
Airaldi, Filippo
Dabiri, Azita
De Schutter, Bart
contents The state of the art for model predictive control (MPC)-based distributed Q-learning is limited to first-order gradient updates of the MPC parameterization. In general, using secondorder information can significantly improve the speed of convergence for learning, allowing the use of higher learning rates without introducing instability. This work presents a second-order extension to MPC-based Q-learning with updates distributed across local agents, relying only on locally available information and neighbor-to-neighbor communication. In simulation the approach is demonstrated to significantly outperform first-order distributed Q-learning.
format Preprint
id arxiv_https___arxiv_org_abs_2511_16424
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Second-Order MPC-Based Distributed Q-Learning
Mallick, Samuel
Airaldi, Filippo
Dabiri, Azita
De Schutter, Bart
Systems and Control
The state of the art for model predictive control (MPC)-based distributed Q-learning is limited to first-order gradient updates of the MPC parameterization. In general, using secondorder information can significantly improve the speed of convergence for learning, allowing the use of higher learning rates without introducing instability. This work presents a second-order extension to MPC-based Q-learning with updates distributed across local agents, relying only on locally available information and neighbor-to-neighbor communication. In simulation the approach is demonstrated to significantly outperform first-order distributed Q-learning.
title Second-Order MPC-Based Distributed Q-Learning
topic Systems and Control
url https://arxiv.org/abs/2511.16424