This paper aims to develop a paradigm that models the learning behavior of intelligent agents (including but not limited to autonomous vehicles, connected and automated vehicles, or human-driven vehicles with intelligent navigation systems where human drivers follow the navigation instructions completely) with a utility-optimizing goal and the system's equilibrating processes in a routing game among atomic selfish agents. Such a paradigm can assist policymakers in devising optimal operational and planning countermeasures under both normal and abnormal circumstances. To this end, we develop a Markov routing game (MRG) in which each agent learns and updates her own en-route path choice policy while interacting with others in transportation networks. To efficiently solve MRG, we formulate it as multi-agent reinforcement learning (MARL) and devise a mean field multi-agent deep Q learning (MF-MA-DQL) approach that captures the competition among agents. The linkage between the classical DUE paradigm and our proposed Markov routing game (MRG) is discussed. We show that the routing behavior of intelligent agents is shown to converge to the classical notion of predictive dynamic user equilibrium (DUE) when traffic environments are simulated using dynamic loading models (DNL). In other words, the MRG depicts DUEs assuming perfect information and deterministic environments propagated by DNL models. Four examples are solved to illustrate the algorithm efficiency and consistency between DUE and the MRG equilibrium, on a simple network without and with spillback, the Ortuzar Willumsen (OW) Network, and a real-world network near Columbia University's campus in Manhattan of New York City.
In the physical design of integrated circuits, global and detailed routing are critical stages involving the determination of the interconnected paths of each net on a circuit while satisfying the design constraints. Existing actual routers as well as routability predictors either have to resort to expensive approaches that lead to high computational times, or use heuristics that do not generalize well. Even though new, learning-based routing methods have been proposed to address this need, requirements on labelled data and difficulties in addressing complex design rule constraints have limite…
Detailed routing is one of the most critical steps in analog circuit design. Complete routing has become increasingly more challenging in advanced node analog circuits, making advances in efficient automatic routers ever more necessary. In this work, we propose a machine learning driven method for solving the track-assignment detailed routing problem for advanced node analog circuits. Our approach adopts an attention-based reinforcement learning (RL) policy model. Our main insight and advancement over this RL model is the use of supervision as a way to leverage solutions generated by a convent…
Georgia Institute of Technology（佐治亚理工学院）；IBM Watson AI Foundation Group（IBM沃森人工智能基金会组）
Applying Machine Learning (ML) techniques to design and optimize computer architectures is a promising research direction. Optimizing the runtime performance of a Network-on-Chip (NoC) necessitates a continuous learning framework. In this work, we demonstrate the promise of applying reinforcement learning (RL) to optimize NoC runtime performance. We present three RL-based methods for learning optimal routing algorithms. The experimental results show the algorithms can successfully learn a near-optimal solution across different environment states. Reproducible Code: github.com/huckiyang/interco…
Pakistan Institute of Engineering and Applied Sciences（巴基斯坦工程与应用科学学院）；Carleton University（卡尔顿大学）
Deep Reinforcement Learning (DRL) uses diverse, unstructured data and makes RL capable of learning complex policies in high dimensional environments. Intelligent Transportation System (ITS) based on Autonomous Vehicles (AVs) offers an excellent playground for policy-based DRL. Deep learning architectures solve computational challenges of traditional algorithms while helping in real-world adoption and deployment of AVs. One of the main challenges in AVs implementation is that it can worsen traffic congestion on roads if not reliably and efficiently managed. Considering each vehicle's holistic e…
Semi-Gradient SARSA Routing with Theoretical Guarantee on Traffic Stability and Weight Convergence
UM Joint Institute（UM联合研究所）；Shanghai Jiao Tong University（上海交通大学）；School of Computer Science, Wuhan University（武汉大学计算机学院）；School of Electronics, Peking University（北京大学电子学院）
We present a novel data-driven approach of learning traffic flow patterns of a transportation network given that many instances of origin to destination (OD) travel demand and link flows of the network are available. Instead of estimating traffic flow patterns assuming certain user behavior (e.g., user equilibrium or system optimal), here we explore the idea of learning those flow patterns directly from the data. To implement this idea, we have formulated the traffic-assignment problem as a data-driven learning problem and developed a neural network-based framework known as Graph Convolutional…
Network traffic classification using machine learning techniques has been widely studied. Most existing schemes classify entire traffic flows, but there are major limitations to their practicality. At a network router, the packets need to be processed with minimum delay, so the classifier cannot wait until the end of the flow to make a decision. Furthermore, a complicated machine learning algorithm can be too computationally expensive to implement inside the router. In this paper, we introduce flow-packet hybrid traffic classification (FPHTC), where the router makes a decision per packet based…
Learning traffic flows: Graph Neural Networks for Metamodelling Traffic Assignment
Department of Technology, Management and Economics, Technical University of Denmark, Lyngby, Denmark（技术、管理与经济系，丹麦技术大学）；Department of Civil, Constructional and Environmental Engineering, Sapienza University of Rome, Rome, Italy（土木、建筑与环境工程系，罗马萨皮恩扎大学）；Department of Aeronautics and Astronautics, Stanford University, Stanford, California（航空与航天系，斯坦福大学）
Hebrew University of Jerusalem（希伯来大学）；Microsoft Research（微软研究院）；Technion（以色列理工学院）
Routing is, arguably, the most fundamental task in computer networking, and the most extensively studied one. A key challenge for routing in real-world environments is the need to contend with uncertainty about future traffic demands. We present a new approach to routing under demand uncertainty: tackling this challenge as stochastic optimization, and employing deep learning to learn complex patterns in traffic demands. We show that our method provably converges to the global optimum in well-studied theoretical models of multicommodity flow. We exemplify the practical usefulness of our approac…
DATA61|CSIRO（联邦科学与工业研究组织数据61所）；University of Technology, Sydney（悉尼科技大学）
The study focuses on estimating and predicting time-varying origin to destination (OD) trip tables for a dynamic traffic assignment (DTA) model. A bi-level optimisation problem is formulated and solved to estimate OD flows from pre-existent demand matrix and historical traffic flow counts. The estimated demand is then considered as an input for a time series OD demand prediction model to support the DTA model for short-term traffic condition forecasting. Results show a high capability of the proposed OD demand estimation method to reduce the DTA model error through an iterative solution algori…
Software Defined Networking (SDN) achieves programmability of a network through separation of the control and data planes. It enables flexibility in network management and control. Energy efficiency is one of the challenging global problems which has both economic and environmental impact. A massive amount of information is generated in the controller of an SDN based network. Machine learning gives the ability to computers to progressively learn from data without having to write specific instructions. In this work, we propose MER-SDN: a machine learning framework for traffic-aware energy effic…
