用强化学习优化蚁群算法，高效求解旅行商问题。
NeuFACO: Neural Focused Ant Colony Optimization for Traveling Salesman Problem
- 结合PPO与图神经网络，实现实例化启发式指导
- 在多种TSP实例上生成高质量解，效率显著提升
- 适合需要快速求解复杂组合优化问题的研究者
本文提出NeuFACO，一种用于旅行商问题（TSP）的非自回归框架，融合先进强化学习与改进的蚁群优化（ACO）。NeuFACO采用带熵正则化的近端策略优化（PPO）训练图神经网络，提供实例特定的启发式引导，并集成于包含候选列表、受限路径精炼和可扩展局部搜索的优化ACO框架中。通过利用缓存推理与ACO的随机探索，NeuFACO在多样化的TSP实例上高效生成高质量解。
原文摘要 · Abstract (English)
This study presents Neural Focused Ant Colony Optimization (NeuFACO), a non-autoregressive framework for the Traveling Salesman Problem (TSP) that combines advanced reinforcement learning with enhanced Ant Colony Optimization (ACO). NeuFACO employs Proximal Policy Optimization (PPO) with entropy regularization to train a graph neural network for instance-specific heuristic guidance, which is integrated into an optimized ACO framework featuring candidate lists, restricted tour refinement, and scalable local search. By leveraging amortized inference alongside ACO stochastic exploration, NeuFACO efficiently produces high-quality solutions across diverse TSP instances.
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。