# Dual-Graph Multi-Agent Reinforcement Learning for Handover Optimization

arXiv: https://arxiv.org/abs/2603.24634 · HTML: https://mlsanity.com/paper/2603.24634/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 40 references that are in the map.
- First posted on arXiv 25 Mar 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Interaction Networks for Learning about Objects, Relations and Physics](https://mlsanity.com/paper/1612.00222/) (2016)
- [ns3-gym: Extending OpenAI Gym for Networking Research](https://mlsanity.com/paper/1810.03943/) (2018)
- [Mobility Management in 5G and Beyond: A Novel Smart Handover with Adaptive Time-to-Trigger and Hysteresis Margin](https://mlsanity.com/paper/2207.01706/) (2022)
- [Scalable Multi-agent Reinforcement Learning Algorithm for Wireless Networks](https://mlsanity.com/paper/2108.00506/) (2021)

## Abstract (arXiv)

HandOver (HO) control in cellular networks is governed by a set of HO control parameters that are traditionally configured through rule-based heuristics. A key parameter for HO optimization is the Cell Individual Offset (CIO), defined for each pair of neighboring cells and used to bias HO triggering decisions. At network scale, tuning CIOs becomes a tightly coupled problem: small changes can redirect mobility flows across multiple neighbors, and static rules often degrade under non-stationary traffic and mobility. We exploit the pairwise structure of CIOs by formulating HO optimization as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP) on the network's dual graph. In this representation, each agent controls a neighbor-pair CIO and observes Key Performance Indicators (KPIs) aggregated over its local dual-graph neighborhood, enabling scalable decentralized decisions while preserving graph locality. Building on this formulation, we propose TD3-D-MA, a discrete Multi-Agent Reinforcement Learning (MARL) variant of the TD3 algorithm with a shared-parameter Graph Neural Network (GNN) actor operating on the dual graph and region-wise double critics for training, improving credit assignment in dense deployments. We evaluate TD3-D-MA in an ns-3 system-level simulator configured with real-world network operator parameters across heterogeneous traffic regimes and network topologies. Results show that TD3-D-MA improves network throughput over standard HO heuristics and centralized RL baselines, and generalizes robustly under topology and traffic shifts.