原文传递
Using reinforcement learning to minimize taxi idle times
| 题名： | Using reinforcement learning to minimize taxi idle times |
| 正文语种： | eng |
| 作者： | Kevin O’Keeffe;Sam Anklesaria;Paolo Santi;Carlo Ratti |
| 作者单位： | Senseable City Lab Massachusetts Institute of Technology;Senseable City Lab Massachusetts Institute of Technology;Senseable City Lab Massachusetts Institute of Technology;Senseable City Lab Massachusetts Institute of Technology |
| 关键词： | Data science;machine learning;networks;optimization;reinforcement learning;taxis |
| 摘要： | Abstract Taxis spend a large amount of time idle, searching for passengers. The routes vacant taxis should follow in order to minimize their idle times are hard to calculate; they depend on complex effects like passenger demand, traffic conditions, and inter-taxi competition. Here we explore if reinforcement learning (RL) can be used for this purpose. Using real-world data from three major cities, we show RL-taxis can indeed learn to minimize their idle times in different environments. In particular, a single RL-taxi competing with a population of regular taxis learns to out-perform its rivals. |
| 出版年： | 2022 |
| 期刊名称： | Journal of Intelligent Transportation Systems |
| 卷： | 26 |
| 期： | 1/6 |
| 页码： | 503-514 |
相关文献
- Modeling Routing Behavior Learning Process for Vacant Taxis in a Congested Urban Traffic Network
- Empirical Behavioral Study of Airport-Serving Taxi Drivers Using Automatic Vehicle Location Data
- Coordinated Ramp Metering with Equity Consideration Using Reinforcement Learning
- A data driven approach to assessing the reliability of using taxicab as probes for Real-Time route selections
- What Lies behind Idle Connection Time in Fast-Charging Public Stations: Evidence from Changshu, China
- Constructing an Autonomous Decision Approach in a Real AIS Environment Using Deep Reinforcement Learning
检索历史
应用推荐
