# Compositional Learning for Modular Multi-Agent Self-Organizing Networks

arXiv: https://arxiv.org/abs/2506.02616 · HTML: https://mlsanity.com/paper/2506.02616/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 17 references that are in the map.
- First posted on arXiv 3 Jun 2025.

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

- [Convex optimization](https://mlsanity.com/paper/2106.01946/) (2021)
- [Addressing Function Approximation Error in Actor-Critic Methods](https://mlsanity.com/paper/1802.09477/) (2018)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Task-Driven Modular Networks for Zero-Shot Compositional Learning](https://mlsanity.com/paper/1905.05908/) (2019)
- [Modular Deep Learning](https://mlsanity.com/paper/2302.11529/) (2023)
- [Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorial](https://mlsanity.com/paper/2011.03615/) (2020)
- [On ADMM in Deep Learning: Convergence and Saturation-Avoidance](https://mlsanity.com/paper/1902.02060/) (2019)
- [Inter-Cell Slicing Resource Partitioning via Coordinated Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2202.12833/) (2022)
- [Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimization](https://mlsanity.com/paper/2203.03227/) (2022)
- [Fast and Scalable Network Slicing by Integrating Deep Learning with Lagrangian Methods](https://mlsanity.com/paper/2401.11731/) (2024)

## Abstract (arXiv)

Self-organizing networks face challenges from complex parameter interdependencies and conflicting objectives. This study introduces two compositional learning approaches-Compositional Deep Reinforcement Learning (CDRL) and Compositional Predictive Decision-Making (CPDM)-and evaluates their performance under training time and safety constraints in multi-agent systems. We propose a modular, two-tier framework with cell-level and cell-pair-level agents to manage heterogeneous agent granularities while reducing model complexity. Numerical simulations reveal a significant reduction in handover failures, along with improved throughput and latency, outperforming conventional multi-agent deep reinforcement learning approaches. The approach also demonstrates superior scalability, faster convergence, higher sample efficiency, and safer training in large-scale self-organizing networks.