Timezone: »

Deep Reinforcement Learning for Online Order Dispatching and Driver Repositioning in Ride-sharing
Zhiwei Qin · Xiaocheng Tang · yan jiao · Chenxi Wang

Wed Dec 05 07:45 AM -- 04:30 PM (PST) @ Room 510 ABCD #D6

In this demonstration, we will present a simulation-based human-computer interaction of deep RL in action on order dispatching and driver repositioning in ride-sharing. Specifically, we will demonstrate through several specially designed domains how we use deep RL to train agents (drivers) to have longer optimization horizon and to cooperate to achieve higher business objective values collectively.

Author Information

Tony Qin (DiDi Chuxing)
Xiaocheng Tang (DiDi AI Labs)
yan jiao (didi chuxing)
Chenxi Wang (DiDi)

More from the Same Authors