A reinforcement learning framework for improving parking decisions in last-mile delivery
IF 3.3
2区 工程技术
Q2 TRANSPORTATION
引用次数: 0
Abstract
This study leverages simulation-optimisation with a Reinforcement Learning (RL) model to analyse the routing behaviour of delivery vehicles (DVs). We conceptualise the system as a stochastic k-arme...改进最后一英里配送中停车决策的强化学习框架
本研究利用仿真优化与强化学习（RL）模型来分析送货车辆（DV）的路由行为。我们将该系统概念化为一个随机k-arme系统。
本文章由计算机程序翻译，如有差异，请以英文原文为准。
求助全文
约1分钟内获得全文
求助全文
来源期刊
Transportmetrica B-Transport Dynamics
TRANSPORTATION SCIENCE & TECHNOLOGY-
CiteScore
5.00
自引率
21.40%
发文量
53
期刊介绍：
Transportmetrica B is an international journal that aims to bring together contributions of advanced research in understanding and practical experience in handling the dynamic aspects of transport systems and behavior, and hence the sub-title is set as “Transport Dynamics”.
Transport dynamics can be considered from various scales and scopes ranging from dynamics in traffic flow, travel behavior (e.g. learning process), logistics, transport policy, to traffic control. Thus, the journal welcomes research papers that address transport dynamics from a broad perspective, ranging from theoretical studies to empirical analysis of transport systems or behavior based on actual data.
The scope of Transportmetrica B includes, but is not limited to, the following: dynamic traffic assignment, dynamic transit assignment, dynamic activity-based modeling, applications of system dynamics in transport planning, logistics planning and optimization, traffic flow analysis, dynamic programming in transport modeling and optimization, traffic control, land-use and transport dynamics, day-to-day learning process (model and behavioral studies), time-series analysis of transport data and demand, traffic emission modeling, time-dependent transport policy analysis, transportation network reliability and vulnerability, simulation of traffic system and travel behavior, longitudinal analysis of traveler behavior, etc.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
