# Learning to Herd Agents Amongst Obstacles: Training Robust Shepherding Behaviors using Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2005.09476 · HTML: https://mlsanity.com/paper/2005.09476/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2020.

## Built on by (most cited first, 4 of 4)

- [Review of Metrics to Measure the Stability, Robustness and Resilience of Reinforcement Learning](https://mlsanity.com/paper/2203.12048/) (2022)
- [Hierarchical Policy-Gradient Reinforcement Learning for Multi-Agent Shepherding Control of Non-Cohesive Targets](https://mlsanity.com/paper/2504.02479/) (2025)
- [Contextually Aware Intelligent Control Agents for Heterogeneous Swarms](https://mlsanity.com/paper/2211.12560/) (2022)
- [Decentralized Shepherding of Non-Cohesive Swarms Through Cluttered Environments via Deep Reinforcement Learning](https://mlsanity.com/paper/2511.21405/) (2025)

## Abstract (arXiv)

Robotic shepherding problem considers the control and navigation of a group of coherent agents (e.g., a flock of bird or a fleet of drones) through the motion of an external robot, called shepherd. Machine learning based methods have successfully solved this problem in an empty environment with no obstacles. Rule-based methods, on the other hand, can handle more complex scenarios in which environments are cluttered with obstacles and allow multiple shepherds to work collaboratively. However, these rule-based methods are fragile due to the difficulty in defining a comprehensive set of rules that can handle all possible cases. To overcome these limitations, we propose the first known learning-based method that can herd agents amongst obstacles. By using deep reinforcement learning techniques combined with the probabilistic roadmaps, we train a shepherding model using noisy but controlled environmental and behavioral parameters. Our experimental results show that the proposed method is robust, namely, it is insensitive to the uncertainties originated from both environmental and behavioral models. Consequently, the proposed method has a higher success rate, shorter completion time and path length than the rule-based behavioral methods have. These advantages are particularly prominent in more challenging scenarios involving more difficult groups and strenuous passages.