Saved in:
Bibliographic Details
Main Authors: Arevalo-Castiblanco, Miguel F., and, Eduardo Mojica-Nava, Uribe, César A.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910590518165504
author Arevalo-Castiblanco, Miguel F.
and, Eduardo Mojica-Nava
Uribe, César A.
author_facet Arevalo-Castiblanco, Miguel F.
and, Eduardo Mojica-Nava
Uribe, César A.
contents We propose a robust adaptive online synchronization method for leader-follower networks of nonlinear heterogeneous agents with system uncertainties and input magnitude saturation. Synchronization is achieved using a Distributed input Magnitude Saturation Adaptive Control with Reinforcement Learning (DMSAC-RL), which improves the empirical performance of policies trained on off-the-shelf models using Reinforcement Learning (RL) strategies. The leader observes the performance of a reference model, and followers observe the states and actions of the agents they are connected to, but not the reference model. The leader and followers may differ from the reference model in which the RL control policy was trained. DMSAC-RL uses an internal loop that adjusts the learned policy for the agents in the form of augmented input to solve the distributed control problem, including input-matched uncertainty parameters. We show that the synchronization error of the heterogeneous network is Uniformly Ultimately Bounded (UUB). Numerical analysis of a network of Multiple Input Multiple Output (MIMO) systems supports our theoretical findings.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03273
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Robust synchronization and policy adaptation for networked heterogeneous agents
Arevalo-Castiblanco, Miguel F.
and, Eduardo Mojica-Nava
Uribe, César A.
Systems and Control
We propose a robust adaptive online synchronization method for leader-follower networks of nonlinear heterogeneous agents with system uncertainties and input magnitude saturation. Synchronization is achieved using a Distributed input Magnitude Saturation Adaptive Control with Reinforcement Learning (DMSAC-RL), which improves the empirical performance of policies trained on off-the-shelf models using Reinforcement Learning (RL) strategies. The leader observes the performance of a reference model, and followers observe the states and actions of the agents they are connected to, but not the reference model. The leader and followers may differ from the reference model in which the RL control policy was trained. DMSAC-RL uses an internal loop that adjusts the learned policy for the agents in the form of augmented input to solve the distributed control problem, including input-matched uncertainty parameters. We show that the synchronization error of the heterogeneous network is Uniformly Ultimately Bounded (UUB). Numerical analysis of a network of Multiple Input Multiple Output (MIMO) systems supports our theoretical findings.
title Robust synchronization and policy adaptation for networked heterogeneous agents
topic Systems and Control
url https://arxiv.org/abs/2409.03273