Efficient Ridesharing Dispatch Using Multi-Agent Reinforcement Learning

TL;DR

This paper introduces a multi-agent reinforcement learning approach using QMIX for efficient ridesharing dispatch, outperforming previous methods in stability, scalability, and adaptability to different environment sizes.

Contribution

The paper presents a novel QMIX-based multi-agent RL method for ridesharing dispatch that improves stability and generalization over existing IDQN approaches.

Findings

Outperforms IDQN baseline on fixed grid size

Generalizes well to different grid sizes

Handles variable numbers of passengers and cars effectively

Abstract

With the advent of ride-sharing services, there is a huge increase in the number of people who rely on them for various needs. Most of the earlier approaches tackling this issue required handcrafted functions for estimating travel times and passenger waiting times. Traditional Reinforcement Learning (RL) based methods attempting to solve the ridesharing problem are unable to accurately model the complex environment in which taxis operate. Prior Multi-Agent Deep RL based methods based on Independent DQN (IDQN) learn decentralized value functions prone to instability due to the concurrent learning and exploring of multiple agents. Our proposed method based on QMIX is able to achieve centralized training with decentralized execution. We show that our model performs better than the IDQN baseline on a fixed grid size and is able to generalize well to smaller or larger grid sizes. Also, our algorithm is able to outperform IDQN baseline in the scenario where we have a variable number of passengers and cars in each episode. Code for our paper is publicly available at: https://github.com/UMich-ML-Group/RL-Ridesharing.