TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Nan, Wang, Zishuo, Huang, Shuyu, Diamantopoulos, Georgios, Tziritas, Nikos, Oikonomou, Panagiotis, Theodoropoulos, Georgios
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911574572138496
author Zhang, Nan
Wang, Zishuo
Huang, Shuyu
Diamantopoulos, Georgios
Tziritas, Nikos
Oikonomou, Panagiotis
Theodoropoulos, Georgios
author_facet Zhang, Nan
Wang, Zishuo
Huang, Shuyu
Diamantopoulos, Georgios
Tziritas, Nikos
Oikonomou, Panagiotis
Theodoropoulos, Georgios
contents Decentralised online learning enables runtime adaptation in cyber-physical multi-agent systems, but when operating conditions change, learned policies often require substantial trial-and-error interaction before recovering performance. To address this, we propose TwinLoop, a simulation-in-the-loop digital twin framework for online multi-agent reinforcement learning. When a context shift occurs, the digital twin is triggered to reconstruct the current system state, initialise from the latest agent policies, and perform accelerated policy improvement with simulation what-if analysis before synchronising updated parameters back to the agents in the physical system. We evaluate TwinLoop in a vehicular edge computing task-offloading scenario with changing workload and infrastructure conditions. The results suggest that digital twins can improve post-shift adaptation efficiency and reduce reliance on costly online trial-and-error.
format Preprint
id arxiv_https___arxiv_org_abs_2604_06610
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning
Zhang, Nan
Wang, Zishuo
Huang, Shuyu
Diamantopoulos, Georgios
Tziritas, Nikos
Oikonomou, Panagiotis
Theodoropoulos, Georgios
Machine Learning
Artificial Intelligence
I.2.11; I.6.3
Decentralised online learning enables runtime adaptation in cyber-physical multi-agent systems, but when operating conditions change, learned policies often require substantial trial-and-error interaction before recovering performance. To address this, we propose TwinLoop, a simulation-in-the-loop digital twin framework for online multi-agent reinforcement learning. When a context shift occurs, the digital twin is triggered to reconstruct the current system state, initialise from the latest agent policies, and perform accelerated policy improvement with simulation what-if analysis before synchronising updated parameters back to the agents in the physical system. We evaluate TwinLoop in a vehicular edge computing task-offloading scenario with changing workload and infrastructure conditions. The results suggest that digital twins can improve post-shift adaptation efficiency and reduce reliance on costly online trial-and-error.
title TwinLoop: Simulation-in-the-Loop Digital Twins for Online Multi-Agent Reinforcement Learning
topic Machine Learning
Artificial Intelligence
I.2.11; I.6.3
url https://arxiv.org/abs/2604.06610