Are the RL methods must be used in the dispatching or reposition??

Discussion

Home Discussion Board KDD CUP 2020: Learning to Dispatch and Reposition on a Mobility-on-Demand Platform Are the RL methods must be used in the dispatching or reposition??

andrewguo

Are the RL methods must be used in the dispatching or reposition??

posted in KDD CUP 2020: Learning to Dispatch and Reposition on a Mobility-on-Demand Platform

2020-04-07 04:54

23 comments

mktal

2020-04-07 08:58

andrewguo

2020-04-07 12:15

tqincomp reply andrewguo

2020-04-08 05:04

Reply

0

<p>No, it doesn’t have to be an RL solution. However, at the end of the Dev Phase (before entering the final Testing Phase), each team will be asked to submit an explanation on how their solution is related to RL in the broad sense (e.g., MDP, Approximate DP, bandits, adaptive control, optimization with long horizon).</p>