提出模块化多智能体自组织网络的组合学习方法，提升系统性能与安全性。
Compositional Learning for Modular Multi-Agent Self-Organizing Networks
- 设计分层模块化框架，按细胞级与成对级管理异构智能体
- 仿真显示切换失败率降低，吞吐量与延迟性能更优
- 适合大规模自组织网络，收敛快且训练更安全
自组织网络面临参数耦合复杂与目标冲突的挑战。本文提出两种组合学习方法——组合深度强化学习（CDRL）与组合预测决策（CPDM），并在多智能体系统中评估其在训练时间与安全约束下的表现。提出一种模块化双层框架，通过细胞级与细胞对级智能体管理异构粒度，降低模型复杂度。数值仿真表明，切换失败显著减少，吞吐量与延迟性能优于传统多智能体深度强化学习方法。该方法还展现出更优可扩展性、更快收敛速度、更高样本效率及更安全的训练过程，适用于大规模自组织网络。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。