Skip to main navigation Skip to search Skip to main content

Is Reinforcement Learning the Choice of Human Learners? A Case Study of Taxi Drivers

  • Menghai Pan
  • , Weixiao Huang
  • , Yanhua Li
  • , Xun Zhou
  • , Zhenming Liu
  • , Jie Bao
  • , Yu Zheng
  • , Jun Luo
  • Worcester Polytechnic Institute
  • University of Iowa
  • College of William and Mary
  • JD Intelligent Cities Research
  • Lenovo

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Learning to make optimal decisions is a common yet complicated task. While computer agents can learn to make decisions by running reinforcement learning (RL), it remains unclear how human beings learn. In this paper, we perform the first data-driven case study on taxi drivers to validate whether humans mimic RL to learn. We categorize drivers into three groups based on their performance trends and analyze the correlations between human drivers and agents trained using RL. We discover that drivers that become more efficient at earning over time exhibit similar learning patterns to those of agents, whereas drivers that become less efficient tend to do the opposite. Our study (1) provides evidence that some human drivers do adapt RL when learning, (2) enhances the deep understanding of taxi drivers' learning strategies, (3) offers a guideline for taxi drivers to improve their earnings, and (4) develops a generic analytical framework to study and validate human learning strategies.

Original languageEnglish
Title of host publicationProceedings of the 28th International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2020
EditorsChang-Tien Lu, Fusheng Wang, Goce Trajcevski, Yan Huang, Shawn Newsam, Li Xiong
PublisherAssociation for Computing Machinery
Pages357-366
Number of pages10
ISBN (Electronic)9781450380195
DOIs
StatePublished - 3 Nov 2020
Externally publishedYes
Event28th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2020 - Virtual, Online, United States
Duration: 3 Nov 20206 Nov 2020

Publication series

NameGIS: Proceedings of the ACM International Symposium on Advances in Geographic Information Systems

Conference

Conference28th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, SIGSPATIAL GIS 2020
Country/TerritoryUnited States
CityVirtual, Online
Period3/11/206/11/20

Keywords

  • human learning strategy
  • reinforcement learning
  • urban computing

Fingerprint

Dive into the research topics of 'Is Reinforcement Learning the Choice of Human Learners? A Case Study of Taxi Drivers'. Together they form a unique fingerprint.

Cite this