# Emergent Cooperative Strategies for Multi-Agent Shepherding via Reinforcement Learning

arXiv: https://arxiv.org/abs/2411.05454 · HTML: https://mlsanity.com/paper/2411.05454/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2024.

## Built on by (most cited first, 2 of 2)

- [Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets](https://mlsanity.com/paper/2504.02479/) (2025)
- [Decentralized Shepherding of Non-Cohesive Swarms Through Cluttered Environments via Deep Reinforcement Learning](https://mlsanity.com/paper/2511.21405/) (2025)

## Abstract (arXiv)

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.