A Better Match for Drivers and Riders: Reinforcement Learning at Lyft

We used reinforcement learning to improve how Lyft matches drivers and riders. The change was implemented globally and led to more than $30 million per year in incremental driver revenue.

cs.LG Computer Science Business

View graph Source

Paper

Similar papers

Timing the Match: A Deep Reinforcement Learning Approach for Ride-Hailing and Ride-Pooling ServicesYiman Bao, Jie Gao, J. He et al.2025 · arXiv.org · 3 citations In Library

Augmenting Decisions of Taxi Drivers through Reinforcement Learning for Improving RevenuesTanvi Verma, Pradeep Varakantham, Sarit Kraus et al.2017 · International Conference on Automated Planning and Scheduling · 72 citations In Library

Optimizing matching time intervals for ride-hailing services using reinforcement learningGuoyang Qin, Qi Luo, Yafeng Yin et al.2021 · Transportation Research Part C: Emerging Technologies · 67 citations In Library

Real-Time Rideshare Driver Supply Values Using Online Reinforcement LearningBenjamin Han, Hyungjun Lee, S. Martin2022 · Knowledge Discovery and Data Mining · 15 citations In Library

Reinforcement Learning for Ridesharing: An Extended SurveyZhiwei Qin, Hongtu Zhu, Jieping Ye2021 · Transportation Research Part C: Emerging Technologies · 128 citations In Library

Reinforcement Learning for Ridesharing: A SurveyZhiwei Qin, Hongtu Zhu, Jieping Ye2021 · International Conference on Intelligent Transportation Systems · 24 citations In Library

Policy Gradient-Based Reinforcement Learning for Driver-Passenger Matching in Ride-Hailing PlatformsS. Pandikumar, Balajee Maram, C. Menaka et al.2026 In Library

Deep Reinforcement Learning for Ride-sharing Dispatching and RepositioningZhiwei Qin, Xiaocheng Tang, Yan Jiao et al.2019 · International Joint Conference on Artificial Intelligence · 12 citations In Library

Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing MarketplaceS. S. Eshkevari, Xiaocheng Tang, Zhiwei Qin et al.2022 · Knowledge Discovery and Data Mining · 35 citations In Library

Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement LearningYan Jiao, Xiaocheng Tang, Zhiwei Qin et al.2021 · arXiv.org · 88 citations In Library

Source of record

arXiv

44B

Welcome.

This panel sticks with you. Pick anything below and it opens right beside it, so you can dig through 60,000-plus records without ever losing your spot here.

Travel 44B

LibraryPapers, policy, standards, statute LabsEvery organization building AI ModelsIntelligence, price, and speed BenchmarksThe evaluation catalog IncidentsAI failures and harms SearchOne field across everything DashboardThe state of AI accountability in NY 44B RegistryThe Art. 44-B compliance portal