Enregistré dans:
Détails bibliographiques
Auteurs principaux: Brambati, Martino, Celani, Antonio, Gherardi, Marco, Ginelli, Francesco
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2506.15587
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910005748301824
author Brambati, Martino
Celani, Antonio
Gherardi, Marco
Ginelli, Francesco
author_facet Brambati, Martino
Celani, Antonio
Gherardi, Marco
Ginelli, Francesco
contents We investigate the emergence of cohesive flocking in open, boundless space using a multi-agent reinforcement learning framework. Agents integrate positional and orientational information from their closest topological neighbours and learn to balance alignment and attractive interactions by optimizing a local cost function that penalizes both excessive separation and close-range crowding. The resulting Vicsek-like dynamics is robust to algorithmic implementation details and yields cohesive collective motion with high polar order. The optimal policy is dominated by strong aligning interactions when agents are sufficiently close to their neighbours, and a flexible combination of alignment and attraction at larger separations. We further characterize the internal structure and dynamics of the resulting groups using liquid-state metrics and neighbour exchange rates, finding qualitative agreement with empirical observations in starling flocks. These results suggest that flocking may emerge in groups of moving agents as an adaptive response to the biological imperatives of staying together while avoiding collisions.
format Preprint
id arxiv_https___arxiv_org_abs_2506_15587
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to flock in open space by avoiding collisions and staying together
Brambati, Martino
Celani, Antonio
Gherardi, Marco
Ginelli, Francesco
Soft Condensed Matter
Multiagent Systems
Biological Physics
We investigate the emergence of cohesive flocking in open, boundless space using a multi-agent reinforcement learning framework. Agents integrate positional and orientational information from their closest topological neighbours and learn to balance alignment and attractive interactions by optimizing a local cost function that penalizes both excessive separation and close-range crowding. The resulting Vicsek-like dynamics is robust to algorithmic implementation details and yields cohesive collective motion with high polar order. The optimal policy is dominated by strong aligning interactions when agents are sufficiently close to their neighbours, and a flexible combination of alignment and attraction at larger separations. We further characterize the internal structure and dynamics of the resulting groups using liquid-state metrics and neighbour exchange rates, finding qualitative agreement with empirical observations in starling flocks. These results suggest that flocking may emerge in groups of moving agents as an adaptive response to the biological imperatives of staying together while avoiding collisions.
title Learning to flock in open space by avoiding collisions and staying together
topic Soft Condensed Matter
Multiagent Systems
Biological Physics
url https://arxiv.org/abs/2506.15587