Deep reinforcement learning in transportation research: A review. (September 2021)

• Record Type: Journal Article
• Authors: Parvez Farazi, Nahid; Zou, Bo; Ahamed, Tanvir; Barua, Limon
• Is Part Of: Transportation research interdisciplinary perspectives. Volume 11(2021)
• Publication Date: 2021-09
• Subjects: Deep reinforcement learning -- Transportation research -- Application domain -- Literature review -- Synthetic discussion; Transportation -- Periodicals; 388.05
• DOI: 10.1016/j.trip.2021.100425
• Languages: English
• ISSNs: 2590-1982

Abstract

Highlights: Review DRL research in transportation given its rapid development and lack of a review. Review DRL applications and adaptations to transportation in seven identified domains. Discuss applicability, strengths, and shortcomings of DRL as it pertains to transportation. Identify common and application-specific issues and suggest future research directions. Provide information on available platforms and features for actual DRL implementation. Abstract: Applying and adapting deep reinforcement learning (DRL) to tackle transportation problems is an emerging interdisciplinary field. While rapidly growing, a comprehensive and synthetic review of existing DRL applications and adaptations in transportation research remains missing. The objective of this paper is to fill this gap. We expose the broad transportation research community to the methodological fundamentals of DRL, and present what have been accomplished in the literature by reviewing a total of 155 relevant papers that have appeared between 2016 and 2020. Based on the review, we further synthesize the applicability, strengths, shortcomings, issues, and directions for future DRL research in transportation, along with a discussion on the available DRL research resources. We hope that this review will serve as a useful reference for the transportation community to better understand DRL and its many potentials to advance research, and to stimulate further explorations in this exciting area.