Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fan, Enguang, Chen, Yifan, Shan, Zihan, Caesar, Matthew, Kim, Jae
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917349718753280
author Fan, Enguang
Chen, Yifan
Shan, Zihan
Caesar, Matthew
Kim, Jae
author_facet Fan, Enguang
Chen, Yifan
Shan, Zihan
Caesar, Matthew
Kim, Jae
contents Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer links. We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE): a centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors. Our architecture encodes local agent state and nearby entities with an agent-entity attention module, and aggregates inter-UAV messages with neighbor self-attention over a distance-limited communication graph. We evaluate primarily on a cooperative relay deployment task (DroneConnect) and secondarily on an adversarial engagement task (DroneCombat). In DroneConnect, the proposed method achieves high coverage under restricted communication and partial observation (e.g. 74% coverage with M = 5 UAVs and N = 10 nodes) while remaining competitive with a mixed-integer linear programming (MILP) optimization-based offline upper bound, and it generalizes to unseen team sizes without fine-tuning. In the adversarial setting, the same framework transfers without architectural changes and improves win rate over non-communicating baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2603_16141
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment
Fan, Enguang
Chen, Yifan
Shan, Zihan
Caesar, Matthew
Kim, Jae
Multiagent Systems
Machine Learning
Networking and Internet Architecture
Autonomous Unmanned Aerial Vehicle (UAV) swarms are increasingly used as rapidly deployable aerial relays and sensing platforms, yet practical deployments must operate under partial observability and intermittent peer-to-peer links. We present a graph-based multi-agent reinforcement learning framework trained under centralized training with decentralized execution (CTDE): a centralized critic and global state are available only during training, while each UAV executes a shared policy using local observations and messages from nearby neighbors. Our architecture encodes local agent state and nearby entities with an agent-entity attention module, and aggregates inter-UAV messages with neighbor self-attention over a distance-limited communication graph. We evaluate primarily on a cooperative relay deployment task (DroneConnect) and secondarily on an adversarial engagement task (DroneCombat). In DroneConnect, the proposed method achieves high coverage under restricted communication and partial observation (e.g. 74% coverage with M = 5 UAVs and N = 10 nodes) while remaining competitive with a mixed-integer linear programming (MILP) optimization-based offline upper bound, and it generalizes to unseen team sizes without fine-tuning. In the adversarial setting, the same framework transfers without architectural changes and improves win rate over non-communicating baselines.
title Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment
topic Multiagent Systems
Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2603.16141