# Synthesizing Decentralized Controllers with Graph Neural Networks and Imitation Learning

arXiv: https://arxiv.org/abs/2012.14906 · HTML: https://mlsanity.com/paper/2012.14906/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 29 Dec 2020.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 30 of 31)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering](https://mlsanity.com/paper/1606.09375/) (2016)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Graph Signal Processing: Overview, Challenges and Applications](https://mlsanity.com/paper/1712.00468/) (2017)
- [Structured Sequence Modeling with Graph Convolutional Recurrent Networks](https://mlsanity.com/paper/1612.07659/) (2016)
- [Stability Properties of Graph Neural Networks](https://mlsanity.com/paper/1905.04497/) (2019)
- [Graphon Neural Networks and the Transferability of Graph Neural Networks](https://mlsanity.com/paper/2006.03548/) (2020)
- [Connecting the Dots: Identifying Network Structure via Graph Signal Processing](https://mlsanity.com/paper/1810.13066/) (2018)
- [Convolutional Neural Network Architectures for Signals Supported on Graphs](https://mlsanity.com/paper/1805.00165/) (2018)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [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)
- [Graphs, Convolutions, and Neural Networks: From Graph Filters to Graph Neural Networks](https://mlsanity.com/paper/2003.03777/) (2020)
- [Optimal Power Flow Using Graph Neural Networks](https://mlsanity.com/paper/1910.09658/) (2019)
- [Learning Decentralized Controllers for Robot Swarms with Graph Neural Networks](https://mlsanity.com/paper/1903.10527/) (2019)
- [Gated Graph Recurrent Neural Networks](https://mlsanity.com/paper/2002.01038/) (2020)
- [Learning an Approximate Model Predictive Controller with Guarantees](https://mlsanity.com/paper/1806.04167/) (2018)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [Stationary Graph Processes and Spectral Estimation](https://mlsanity.com/paper/1603.04667/) (2016)
- [EdgeNets:Edge Varying Graph Neural Networks](https://mlsanity.com/paper/2001.07620/) (2020)
- [Imitation Learning with Stability and Safety Guarantees](https://mlsanity.com/paper/2012.09293/) (2020)
- [Stationary signal processing on graphs](https://mlsanity.com/paper/1601.02522/) (2016)
- [Graph Policy Gradients for Large Scale Robot Control](https://mlsanity.com/paper/1907.03822/) (2019)
- [Forecasting Time Series with VARMA Recursions on Graphs](https://mlsanity.com/paper/1810.08581/) (2018)
- [A Time-Vertex Signal Processing Framework](https://mlsanity.com/paper/1705.02307/) (2017)
- [Filtering Random Graph Processes Over Random Time-Varying Graphs](https://mlsanity.com/paper/1705.00442/) (2017)
- [Wide and Deep Graph Neural Networks with Distributed Online Learning](https://mlsanity.com/paper/2006.06376/) (2020)
- [Graph Neural Networks for Distributed Linear-Quadratic Control](https://mlsanity.com/paper/2011.05360/) (2020)
- [Ergodicity in Stationary Graph Processes: A Weak Law of Large Numbers](https://mlsanity.com/paper/1803.04550/) (2018)

## Built on by (most cited first, 12 of 12)

- [Graph Filters for Signal Processing and Machine Learning on Graphs](https://mlsanity.com/paper/2211.08854/) (2022)
- [Wide and Deep Graph Neural Network with Distributed Online Learning](https://mlsanity.com/paper/2107.09203/) (2021)
- [Space-Time Graph Neural Networks](https://mlsanity.com/paper/2110.02880/) (2021)
- [Unsupervised Learning of Sampling Distributions for Particle Filters](https://mlsanity.com/paper/2302.01174/) (2023)
- [Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks](https://mlsanity.com/paper/2106.13358/) (2021)
- [Learning-based Motion Planning in Dynamic Environments Using GNNs and Temporal Encoding](https://mlsanity.com/paper/2210.08408/) (2022)
- [Graph learning in robotics: a survey](https://mlsanity.com/paper/2310.04294/) (2023)
- [LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control](https://mlsanity.com/paper/2401.04855/) (2024)
- [Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks](https://mlsanity.com/paper/2302.08447/) (2023)
- [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)
- [Real-Time Risky Fault-Chain Search using Time-Varying Graph RNNs](https://mlsanity.com/paper/2503.09775/) (2025)

## Abstract (arXiv)

Dynamical systems consisting of a set of autonomous agents face the challenge of having to accomplish a global task, relying only on local information. While centralized controllers are readily available, they face limitations in terms of scalability and implementation, as they do not respect the distributed information structure imposed by the network system of agents. Given the difficulties in finding optimal decentralized controllers, we propose a novel framework using graph neural networks (GNNs) to learn these controllers. GNNs are well-suited for the task since they are naturally distributed architectures and exhibit good scalability and transferability properties. We show that GNNs learn appropriate decentralized controllers by means of imitation learning, leverage their permutation invariance properties to successfully scale to larger teams and transfer to unseen scenarios at deployment time. The problems of flocking and multi-agent path planning are explored to illustrate the potential of GNNs in learning decentralized controllers.