Galedra
Sign in Sign up

Evidence item

Uber describes modelling its own matching system to match drivers to riders. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 4748

Source: Reinforcement Learning for Modeling Marketplace Balance · locator {} · excerpt hash sha256:f8ad877d147fe44ce8b77b6dd60148da0eab29770ef62009e1accd5c0c1c62a6

Exact excerpt
We model the Uber matching system in an MDP (Markov Decision Process) framework where the agent takes collective decisions to match drivers to riders in a particular order.

Linked claims

ClaimDirectionRelevanceStepsCounted
b14de16bCONTRADICTSTRONG1yes

Audits

None.