# Learning Decentralized Strategies for a Perimeter Defense Game with Graph Neural Networks

arXiv: https://arxiv.org/abs/2211.01757 · HTML: https://mlsanity.com/paper/2211.01757/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 33 references that are in the map.
- First posted on arXiv 24 Sep 2022.

## Builds on (most cited first, 17 of 17)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Convolutional Neural Network Architectures for Signals Supported on Graphs](https://mlsanity.com/paper/1805.00165/) (2018)
- [Graph Neural Networks: Architectures, Stability and Transferability](https://mlsanity.com/paper/2008.01767/) (2020)
- [Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks](https://mlsanity.com/paper/1903.10527/) (2019)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [SLOAM: Semantic Lidar Odometry and Mapping for Forest Inventory](https://mlsanity.com/paper/1912.12726/) (2019)
- [Resilient Active Target Tracking with Multiple Robots](https://mlsanity.com/paper/1809.04032/) (2018)
- [MAVNet: an Effective Semantic Segmentation Micro-Network for MAV-based Tasks](https://mlsanity.com/paper/1904.01795/) (2019)
- [Decentralization of Multiagent Policies by Learning What to Communicate](https://mlsanity.com/paper/1901.08490/) (2019)
- [Defending a Perimeter from a Ground Intruder Using an Aerial Defender: Theory and Practice](https://mlsanity.com/paper/2109.02852/) (2021)
- [Robust Multi-Robot Active Target Tracking Against Sensing and Communication Attacks](https://mlsanity.com/paper/2109.09838/) (2021)
- [Matching-Based Capture Strategies for 3D Heterogeneous Multiplayer Reach-Avoid Differential Games](https://mlsanity.com/paper/1909.11881/) (2019)
- [Perimeter-defense Game between Aerial Defender and Ground Intruder](https://mlsanity.com/paper/2012.14980/) (2020)
- [Guarding a Target Set from a Single Attacker in the Euclidean Space](https://mlsanity.com/paper/2109.07075/) (2021)
- [UAV-Assisted Heterogeneous Networks for Capacity Enhancement](https://mlsanity.com/paper/1604.02559/) (2016)
- [Active Target Tracking with Self-Triggered Communications in Multi-Robot Teams](https://mlsanity.com/paper/1704.07475/) (2017)
- [Sensor Assignment Algorithms to Improve Observability while Tracking Targets](https://mlsanity.com/paper/1709.06428/) (2017)

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

- [Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense](https://mlsanity.com/paper/2301.09689/) (2023)
- [Embedded Mean Field Reinforcement Learning for Perimeter-defense Game](https://mlsanity.com/paper/2505.14209/) (2025)

## Abstract (arXiv)

We consider the problem of finding decentralized strategies for multi-agent perimeter defense games. In this work, we design a graph neural network-based learning framework to learn a mapping from defenders' local perceptions and the communication graph to defenders' actions such that the learned actions are close to that generated by a centralized expert algorithm. We demonstrate that our proposed networks stay closer to the expert policy and are superior to other baseline algorithms by capturing more intruders. Our GNN-based networks are trained at a small scale and can generalize to large scales. To validate our results, we run perimeter defense games in scenarios with different team sizes and initial configurations to evaluate the performance of the learned networks.