1. cGAIL: <u>C</u>onditional <u>G</u>enerative <u>A</u>dversarial <u>I</u>mitation <u>L</u>earning—An Application in Taxi Drivers’ Strategy Learning
- Author
-
Xin Zhang, Jun Luo, Yanhua Li, and Xun Zhou
- Subjects
Information Systems and Management ,Operations research ,business.industry ,Computer science ,Quality of service ,02 engineering and technology ,010501 environmental sciences ,01 natural sciences ,Adversarial system ,020204 information systems ,Urban computing ,Public transport ,0202 electrical engineering, electronic engineering, information engineering ,Trajectory ,Global Positioning System ,business ,Baseline (configuration management) ,Generative grammar ,0105 earth and related environmental sciences ,Information Systems - Abstract
Smart passenger-seeking strategies employed by taxi drivers contribute not only to drivers’ incomes, but also higher quality of service passengers received. Therefore, understanding taxi drivers’ behaviors and learning the good passenger-seeking strategies are crucial to boost taxi drivers’ well-being and public transportation quality of service. However, we observe that drivers’ preferences of choosing which area to find the next passenger are diverse and dynamic across locations and drivers. It is hard to learn the location-dependent preferences given the partial data (i.e., an individual driver's trajectory may not cover all locations). In this paper, we make the first attempt to develop conditional generative adversarial imitation learning (cGAIL) model, as a unifying collective inverse reinforcement learning framework that learns the driver's decision-making preferences and policies by transferring knowledge across taxi driver agents and across locations. Our evaluation results on three months of taxi GPS trajectory data in Shenzhen, China, demonstrate that the driver's preferences and policies learned from cGAIL are on average 34.7% more accurate than those learned from other state-of-the-art baseline approaches.
- Published
- 2022