mlsanityData to 14 Oct 2026

Compositional Learning for Modular Multi-Agent Self-Organizing Networks

arXiv 2506.02616 ↗First posted 3 Jun 2025cs.LGcited by 0

Not on the map. Why?

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.

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

10 of 17 references.

References · 10

  1. 2021Convex optimizationcited by 2,515
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2017Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environmentscited by 1,558
  4. 2019Task-Driven Modular Networks for Zero-Shot Compositional Learningcited by 121
  5. 2023Modular Deep Learningcited by 83
  6. 2020Single and Multi-Agent Deep Reinforcement Learning for AI-Enabled Wireless Networks: A Tutorialcited by 60
  7. 2019On ADMM in Deep Learning: Convergence and Saturation-Avoidancecited by 15
  8. 2022Inter-Cell Slicing Resource Partitioning via Coordinated Multi-Agent Deep Reinforcement Learningcited by 5
  9. 2022Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimizationcited by 2
  10. 2024Fast and Scalable Network Slicing by Integrating Deep Learning with Lagrangian Methodscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Hypernetwork-based approach for optimal composition design in partially controlled multi-agent systems
  2. 2025Deep Meta Coordination Graphs for Multi-agent Reinforcement Learning
  3. 2025Emergence of Hierarchies in Multi-Agent Self-Organizing Systems Pursuing a Joint Objective
  4. 2025Deep Reinforcement Learning for Multi-Agent Coordination
  5. 2025Self-Evolving Multi-Agent Systems via Textual Backpropagation
  6. 2024Learning Emergence of Interaction Patterns across Independent RL Agents in Multi-Agent Environments
  7. 2026MO-MIX: Multi-Objective Multi-Agent Cooperative Decision-Making With Deep Reinforcement Learning
  8. 2025Reinforcement Networks: novel framework for collaborative Multi-Agent Reinforcement Learning tasks