Emergent Cooperative Strategies for Multi-Agent Shepherding via Reinforcement Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Napolitano, Italo, Lama, Andrea, De Lellis, Francesco, di Bernardo, Mario
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911403020910592
author Napolitano, Italo
Lama, Andrea
De Lellis, Francesco
di Bernardo, Mario
author_facet Napolitano, Italo
Lama, Andrea
De Lellis, Francesco
di Bernardo, Mario
contents We present a decentralized reinforcement learning (RL) approach to address the multi-agent shepherding control problem, departing from the conventional assumption of cohesive target groups. Our two-layer control architecture consists of a low-level controller that guides each herder to contain a specific target within a goal region, while a high-level layer dynamically selects from multiple targets the one an herder should aim at corralling and containing. Cooperation emerges naturally, as herders autonomously choose distinct targets to expedite task completion. We further extend this approach to large-scale systems, where each herder applies a shared policy, trained with few agents, while managing a fixed subset of agents.
format Preprint
id arxiv_https___arxiv_org_abs_2411_05454
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Emergent Cooperative Strategies for Multi-Agent Shepherding via Reinforcement Learning
Napolitano, Italo
Lama, Andrea
De Lellis, Francesco
di Bernardo, Mario
Systems and Control
We present a decentralized reinforcement learning (RL) approach to address the multi-agent shepherding control problem, departing from the conventional assumption of cohesive target groups. Our two-layer control architecture consists of a low-level controller that guides each herder to contain a specific target within a goal region, while a high-level layer dynamically selects from multiple targets the one an herder should aim at corralling and containing. Cooperation emerges naturally, as herders autonomously choose distinct targets to expedite task completion. We further extend this approach to large-scale systems, where each herder applies a shared policy, trained with few agents, while managing a fixed subset of agents.
title Emergent Cooperative Strategies for Multi-Agent Shepherding via Reinforcement Learning
topic Systems and Control
url https://arxiv.org/abs/2411.05454