Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Azagirre et al. (2024) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: