学习移动城市：用于城市网络校准与控制的深度元模型和强化策略
Learning to Move Cities: Deep Meta-Models and Reinforcement Policies for Calibration and Control in Urban Networks
浏览论文内容
中文总结 AI 辅助
本文提出共享潜在空间框架，结合MLP-自编码器与深度Q学习，实现城市交通模拟器校准和动态控制，在基准网络上将系统出行时间降低最多51%。
中文摘要 AI 辅助
城市交通网络面临复杂的优化挑战，涵盖高保真模拟器的校准和实时运营控制。本文提出了一个共享潜在空间框架，通过城市交通动态的通用学习表示，将模拟器校准与强化学习控制连接起来。首先，我们开发了一种组合式MLP-自编码器架构，学习连接模拟器输入（起点-终点需求、网络参数）与输出（出行时间、拥堵模式）的低维流形，从而实现高效的贝叶斯优化校准。与传统降维方法相比，该方法展现出优越的样本效率，在固定计算预算内实现了对观测数据更好的拟合。其次，我们实现了一个具有经验回放和目标网络的深度Q学习智能体，通过调度和路径调整优化动态交通分配。在基准网络的实证评估中，与基线运营相比，我们的方法将系统范围的出行时间最多降低了51%。学习到的潜在表示不仅用于降低贝叶斯校准的维度，还被纳入强化学习状态表示中，使控制策略能够在压缩且校准的交通动态上运行。这种共享潜在空间公式为智能交通系统中从模拟器校准到自适应运营控制提供了统一路径。我们的结果凸显了深度学习方法在城市出行规划与管理中的变革潜力，特别是在传统优化方法面临计算瓶颈的大规模网络中。
英文摘要
Urban transportation networks present complex optimization challenges spanning calibration of high-fidelity simulators and real-time operational control. This paper presents a shared latent-space framework that connects simulator calibration and reinforcement learning control through a common learned representation of urban traffic dynamics. First, we develop a combinatorial MLP-autoencoder architecture that learns low-dimensional manifolds linking simulator inputs (origin-destination demand, network parameters) to outputs (travel times, congestion patterns), enabling efficient Bayesian optimization for calibration. This approach demonstrates superior sample efficiency compared to traditional dimension reduction methods, achieving better fit to observational data within fixed computational budgets. Second, we implement a deep Q-learning agent with experience replay and target networks to optimize dynamic traffic assignment through scheduling and routing adjustments. In empirical evaluations on benchmark networks, our approach reduces system-wide travel times by up to 51% compared to baseline operations. The learned latent representation is not only used to reduce the dimensionality of Bayesian calibration, but is also incorporated into the reinforcement learning state representation, allowing the control policy to operate on compressed and calibrated traffic dynamics. This shared latent-space formulation provides a unified pathway from simulator calibration to adaptive operational control within intelligent transportation systems. Our results highlight the transformative potential of deep learning methods in urban mobility planning and management, particularly for large-scale networks where traditional optimization approaches face computational bottlenecks.
发表机构
- George Mason University（乔治梅森大学）
- University of South Dakota（南达科他大学）
- Syracuse University（雪城大学）
- Federal University of Technology Akure（联邦理工大学阿库雷分校）
机构由 AI 辅助整理，请以论文原文为准。
