# MAGNNET: Multi-Agent Graph Neural Network-based Efficient Task Allocation for Autonomous Vehicles with Deep Reinforcement Learning

arXiv: https://arxiv.org/abs/2502.02311 · HTML: https://mlsanity.com/paper/2502.02311/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Cooperative and V2X driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 10 of its 22 references that are in the map.
- First posted on arXiv 4 Feb 2025.

## Placed in

- End-to-end autonomous driving / [Cooperative and V2X driving](https://mlsanity.com/driving/cooperative-and-v2x-driving/)

## Builds on (most cited first, 10 of 10)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [RTAW: An Attention Inspired Reinforcement Learning Method for Multi-Robot Task Allocation in Warehouse Environments](https://mlsanity.com/paper/2209.05738/) (2022)
- [A Framework for Real-World Multi-Robot Systems Running Decentralized GNN-Based Policies](https://mlsanity.com/paper/2111.01777/) (2021)
- [Greedy Decentralized Auction-based Task Allocation for Multi-Agent Systems](https://mlsanity.com/paper/2107.00144/) (2021)
- [Graph-based Decentralized Task Allocation for Multi-Robot Target Localization](https://mlsanity.com/paper/2309.08896/) (2023)
- [TornadoDrone: Bio-inspired DRL-based Drone Landing on 6D Platform with Wind Force Disturbances](https://mlsanity.com/paper/2406.16164/) (2024)
- [Research on Multi-Agent Communication and Collaborative Decision-Making Based on Deep Reinforcement Learning](https://mlsanity.com/paper/2305.17141/) (2023)
- [Dynamic Subgoal based Path Formation and Task Allocation: A NeuroFleets Approach to Scalable Swarm Robotics](https://mlsanity.com/paper/2409.00766/) (2024)

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

- [Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities](https://mlsanity.com/paper/2506.18019/) (2025)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [Can a Robot Walk the Robotic Dog: Triple-Zero Collaborative Navigation for Heterogeneous Multi-Agent Systems](https://mlsanity.com/paper/2603.21723/) (2026)
- [ARMATA: Auto-Regressive Multi-Agent Task Assignment](https://mlsanity.com/paper/2605.04225/) (2026)

## Abstract (arXiv)

This paper addresses the challenge of decentralized task allocation within heterogeneous multi-agent systems operating under communication constraints. We introduce a novel framework that integrates graph neural networks (GNNs) with a centralized training and decentralized execution (CTDE) paradigm, further enhanced by a tailored Proximal Policy Optimization (PPO) algorithm for multi-agent deep reinforcement learning (MARL). Our approach enables unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) to dynamically allocate tasks efficiently without necessitating central coordination in a 3D grid environment. The framework minimizes total travel time while simultaneously avoiding conflicts in task assignments. For the cost calculation and routing, we employ reservation-based A* and R* path planners. Experimental results revealed that our method achieves a high 92.5% conflict-free success rate, with only a 7.49% performance gap compared to the centralized Hungarian method, while outperforming the heuristic decentralized baseline based on greedy approach. Additionally, the framework exhibits scalability with up to 20 agents with allocation processing of 2.8 s and robustness in responding to dynamically generated tasks, underscoring its potential for real-world applications in complex multi-agent scenarios.