Learning to flock in open space by avoiding collisions and staying together

TL;DR

This paper demonstrates that multi-agent reinforcement learning can produce cohesive, flocking behavior in open space, balancing alignment and attraction to mimic natural bird flocks.

Contribution

It introduces a novel RL-based approach that results in robust, cohesive flocking dynamics similar to biological systems, with insights into the underlying interaction mechanisms.

Findings

Emergence of Vicsek-like flocking behavior in open space.

Flocking dynamics are robust to implementation details.

Internal group structure aligns with empirical bird flock observations.

Abstract

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.