BriefGPT.xyz
Jan, 2024
图形 Q-Learning 用于组合优化
Graph Q-Learning for Combinatorial Optimization
HTML
PDF
Victoria M. Dax, Jiachen Li, Kevin Leahy, Mykel J. Kochenderfer
TL;DR
本论文提出并证明了图神经网络可以应用于解决组合优化问题，通过将优化过程视为顺序决策问题，使用Q-Learning训练图神经网络可以在参数和训练时间上只占一小部分的情况下接近达到最先进的启发式求解器的性能。
Abstract
graph-structured data
is ubiquitous throughout natural and social sciences, and
graph neural networks
(GNNs) have recently been shown to be effective at solving prediction and inference problems on graph data. In
→