论文标题
在图形上进行物流优化的图表上强大的增强学习
Robust Reinforcement Learning on Graphs for Logistics optimization
论文作者
论文摘要
如今，物流优化已成为AI社区中最热门的领域之一。在过去的一年中，通过以图形形式来表示该问题可以实现域中的重大进步。研究的另一个有希望的领域是将增强学习算法应用于上述任务。在我们的工作中，我们利用了两种方法，并在图表上应用强化学习。为此，我们已经分析了从图形神经网络和增强学习中的领域和选定的SOTA算法中的最新结果。然后，我们将选定的模型结合在纽约市运输网络的AMOD系统优化问题上。我们的团队比较了三种算法 - GAT，Pro -CNN和PTDNET-将图表表示的重要节点提升到了重要的节点。最后，我们在AMOD系统优化问题上实现了SOTA结果，该问题是使用GNN的PTDNET，并以增强方式训练它们。 关键字：图形神经网络（GNN），物流优化，增强学习
Logistics optimization nowadays is becoming one of the hottest areas in the AI community. In the past year, significant advancements in the domain were achieved by representing the problem in a form of graph. Another promising area of research was to apply reinforcement learning algorithms to the above task. In our work, we made advantage of using both approaches and apply reinforcement learning on a graph. To do that, we have analyzed the most recent results in both fields and selected SOTA algorithms both from graph neural networks and reinforcement learning. Then, we combined selected models on the problem of AMOD systems optimization for the transportation network of New York city. Our team compared three algorithms - GAT, Pro-CNN and PTDNet - to bring to the fore the important nodes on a graph representation. Finally, we achieved SOTA results on AMOD systems optimization problem employing PTDNet with GNN and training them in reinforcement fashion. Keywords: Graph Neural Network (GNN), Logistics optimization, Reinforcement Learning
