一种用于资源分配问题的新型开关型策略网络：技术报告
A Novel Switch-Type Policy Network for Resource Allocation Problems: Technical Report
AI总结：
本文提出一种开关型神经网络（STN）替代MLP，用于提升排队网络中深度强化学习策略的样本效率与泛化能力，在熟悉环境匹配MLP性能，在新环境中显著超越。
摘要：
深度强化学习（DRL）已成为在排队网络中开发控制策略的强大工具，但这些应用中常用的多层感知器（MLP）神经网络存在显著缺点。MLP架构虽然通用，但往往存在样本效率低下和容易过度拟合训练环境的倾向，导致在新颖的、未见过的网络上性能欠佳。针对这些问题，我们引入了一种开关型神经网络（STN）架构，旨在提高排队网络中DRL策略的效率和泛化能力。STN利用传统非学习策略中的结构模式，确保在相似状态下动作选择的一致性。这种设计不仅简化了学习过程，还通过减少过度拟合的倾向促进了更好的泛化。我们的工作提出了三项关键贡献：第一，开发了STN作为MLP的更有效替代方案；第二，实证证据表明STN在各种训练场景中实现了更优的样本效率；第三，实验结果表明，STN在熟悉环境中的性能与MLP相当，并在新环境中显著优于MLP。通过嵌入领域特定知识，STN在不牺牲性能的情况下增强了近端策略优化（PPO）算法的有效性，表明其适用于广泛的排队网络控制问题。
英文摘要：
Deep Reinforcement Learning (DRL) has become a powerful tool for developing control policies in queueing networks, but the common use of Multi-layer Perceptron (MLP) neural networks in these applications has significant drawbacks. MLP architectures, while versatile, often suffer from poor sample efficiency and a tendency to overfit training environments, leading to suboptimal performance on new, unseen networks. In response to these issues, we introduce a switch-type neural network (STN) architecture designed to improve the efficiency and generalization of DRL policies in queueing networks. The STN leverages structural patterns from traditional non-learning policies, ensuring consistent action choices across similar states. This design not only streamlines the learning process but also fosters better generalization by reducing the tendency to overfit. Our works presents three key contributions: first, the development of the STN as a more effective alternative to MLPs; second, empirical evidence showing that STNs achieve superior sample efficiency in various training scenarios; and third, experimental results demonstrating that STNs match MLP performance in familiar environments and significantly outperform them in new settings. By embedding domain-specific knowledge, the STN enhances the Proximal Policy Optimization (PPO) algorithm's effectiveness without compromising performance, suggesting its suitability for a wide range of queueing network control problems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
