Patent · US Active

Multi-agent reinforcement learning for order-dispatching via order-vehicle distribution matching

US11631333B2 · kind B2 · utility

1Cited by

2References

19Claims

0Family size

Assignee

BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD. · CN

Inventors

Chenxi Wang · Beijing, CN
Zhiwei Qin · Longbeilingcun, CN

Key dates

Filing date	Dec 19, 2019
Grant date	Apr 18, 2023
Priority date	—
Expiry date	Sep 7, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06Q10/08355
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Multi-agent reinforcement learning may be used for rider order-dispatching via matching the distribution of orders and vehicles. Information may be obtained. The information may include a plurality of vehicle locations of a plurality of vehicles, a plurality of ride orders, and a current time. The obtained information may be input into a trained model. The trained model may be based on Kullback-Leibler divergence optimization and independent agents under a guidance of a joint policy. A plurality of order-dispatching tasks may be generated for the plurality of vehicles to fulfill.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.