# Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection

arXiv: https://arxiv.org/abs/2105.08601 · HTML: https://mlsanity.com/paper/2105.08601/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 32 references that are in the map.
- First posted on arXiv 18 May 2021.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents](https://mlsanity.com/paper/1802.08757/) (2018)
- [When2com: Multi-Agent Perception via Communication Graph Grouping](https://mlsanity.com/paper/2006.00176/) (2020)
- [Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability](https://mlsanity.com/paper/1703.06182/) (2017)
- [Who2com: Collaborative Perception via Learnable Handshake Communication](https://mlsanity.com/paper/2003.09575/) (2020)
- [Convolutional Neural Network Architectures for Signals Supported on Graphs](https://mlsanity.com/paper/1805.00165/) (2018)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [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)
- [Graph Policy Gradients for Large Scale Robot Control](https://mlsanity.com/paper/1907.03822/) (2019)
- [The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2008.02616/) (2020)
- [Distributed Submodular Maximization with Limited Information](https://mlsanity.com/paper/1706.04082/) (2017)
- [Resilient Active Target Tracking with Multiple Robots](https://mlsanity.com/paper/1809.04032/) (2018)
- [Adaptive Information Gathering via Imitation Learning](https://mlsanity.com/paper/1705.07834/) (2017)
- [Multi-Agent Discrete Search with Limited Visibility](https://mlsanity.com/paper/1709.03640/) (2017)

## Built on by (most cited first, 14 of 14)

- [Graph Neural Networks in IoT: A Survey](https://mlsanity.com/paper/2203.15935/) (2022)
- [Large Language Models for Multi-Robot Systems: A Survey](https://mlsanity.com/paper/2502.03814/) (2025)
- [Graph Neural Networks for Multi-Robot Active Information Acquisition](https://mlsanity.com/paper/2209.12091/) (2022)
- [A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies](https://mlsanity.com/paper/2111.01777/) (2021)
- [Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation](https://mlsanity.com/paper/2210.09378/) (2022)
- [LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control](https://mlsanity.com/paper/2401.04855/) (2024)
- [Learning Decentralized Flocking Controllers with Spatio-Temporal Graph Neural Network](https://mlsanity.com/paper/2309.17437/) (2023)
- [Decentralized Multi-Agent Active Search and Tracking when Targets Outnumber Agents](https://mlsanity.com/paper/2401.03154/) (2024)
- [Graph Neural Networks Gone Hogwild](https://mlsanity.com/paper/2407.00494/) (2024)
- [A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops](https://mlsanity.com/paper/2309.10164/) (2023)
- [Improving Zero-Shot ObjectNav with Generative Communication](https://mlsanity.com/paper/2408.01877/) (2024)
- [Generalizability of Graph Neural Networks for Decentralized Unlabeled Motion Planning](https://mlsanity.com/paper/2409.19829/) (2024)
- [Neural Observation Field Guided Hybrid Optimization of Camera Placement](https://mlsanity.com/paper/2412.08266/) (2024)
- [From Euclidean to Graph-Structured Data: A Survey of Collaborative Learning](https://mlsanity.com/paper/2609.02984/) (2026)

## Abstract (arXiv)

The problem of decentralized multi-robot target tracking asks for jointly selecting actions, e.g., motion primitives, for the robots to maximize target tracking performance with local communications. One major challenge for practical implementations is to make target tracking approaches scalable for large-scale problem instances. In this work, we propose a general-purpose learning architecture toward collaborative target tracking at scale, with decentralized communications. Particularly, our learning architecture leverages a graph neural network (GNN) to capture local interactions of the robots and learns decentralized decision-making for the robots. We train the learning model by imitating an expert solution and implement the resulting model for decentralized action selection involving local observations and communications only. We demonstrate the performance of our GNN-based learning approach in a scenario of active target tracking with large networks of robots. The simulation results show our approach nearly matches the tracking performance of the expert algorithm, and yet runs several orders faster with up to 100 robots. Moreover, it slightly outperforms a decentralized greedy algorithm but runs faster (especially with more than 20 robots). The results also exhibit our approach's generalization capability in previously unseen scenarios, e.g., larger environments and larger networks of robots.