Multi-Objective Vehicle Rebalancing for Ridehailing System using a Reinforcement Learning Approach

TL;DR

This paper develops a reinforcement learning-based rebalancing algorithm for large-scale ridehailing systems with asymmetric demand, aiming to minimize passenger wait times and vehicle miles traveled in a complex urban environment.

Contribution

It introduces a novel deep reinforcement learning approach to solve a semi Markov decision problem for vehicle rebalancing in ridehailing systems with asymmetric demand.

Findings

The RL-based policy outperforms traditional algorithms in minimizing passenger wait times.

The approach effectively balances vehicle distribution and reduces empty miles.

Results demonstrate the method's applicability to large-scale, real-world scenarios.

Abstract

The problem of designing a rebalancing algorithm for a large-scale ridehailing system with asymmetric demand is considered here. We pose the rebalancing problem within a semi Markov decision problem (SMDP) framework with closed queues of vehicles serving stationary, but asymmetric demand, over a large city with multiple nodes (representing neighborhoods). We assume that the passengers queue up at every node until they are matched with a vehicle. The goal of the SMDP is to minimize a convex combination of the waiting time of the passengers and the total empty vehicle miles traveled. The resulting SMDP appears to be difficult to solve for closed-form expression for the rebalancing strategy. As a result, we use a deep reinforcement learning algorithm to determine the approximately optimal solution to the SMDP. The trained policy is compared with other well-known algorithms for rebalancing, which are designed to address other objectives (such as to minimize demand drop probability) for the ridehailing problem.