# Federated Multi-Agent Deep Reinforcement Learning for Dynamic and Flexible 3D Operation of 5G Multi-MAP Networks

arXiv: https://arxiv.org/abs/2307.06842 · HTML: https://mlsanity.com/paper/2307.06842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 19 references that are in the map.
- First posted on arXiv 30 Jun 2023.

## Builds on (most cited first, 7 of 7)

- [Joint Trajectory and Communication Design for Multi-UAV Enabled Wireless Networks](https://mlsanity.com/paper/1705.02723/) (2017)
- [Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks](https://mlsanity.com/paper/2005.12394/) (2020)
- [Efficient 3D Aerial Base Station Placement Considering Users Mobility by Reinforcement Learning](https://mlsanity.com/paper/1801.07472/) (2018)
- [Transferable and Distributed User Association Policies for 5G and Beyond Networks](https://mlsanity.com/paper/2106.02540/) (2021)
- [Dual-Attention Deep Reinforcement Learning for Multi-MAP 3D Trajectory Optimization in Dynamic 5G Networks](https://mlsanity.com/paper/2303.05233/) (2023)
- [On-Demand Deployment of Multiple Aerial Base Stations for Traffic Offloading and Network Recovery](https://mlsanity.com/paper/1807.02009/) (2018)
- [Learning Hierarchical Resource Allocation and Multi-agent Coordination of 5G mobile IAB Nodes](https://mlsanity.com/paper/2302.07573/) (2023)

## Abstract (arXiv)

This paper addresses the efficient management of Mobile Access Points (MAPs), which are Unmanned Aerial Vehicles (UAV), in 5G networks. We propose a two-level hierarchical architecture, which dynamically reconfigures the network while considering Integrated Access-Backhaul (IAB) constraints. The high-layer decision process determines the number of MAPs through consensus, and we develop a joint optimization process to account for co-dependence in network self-management. In the low-layer, MAPs manage their placement using a double-attention based Deep Reinforcement Learning (DRL) model that encourages cooperation without retraining. To improve generalization and reduce complexity, we propose a federated mechanism for training and sharing one placement model for every MAP in the low-layer. Additionally, we jointly optimize the placement and backhaul connectivity of MAPs using a multi-objective reward function, considering the impact of varying MAP placement on wireless backhaul connectivity.