Efficient Ridesharing Dispatch Using Multi-Agent Reinforcement Learning

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. * indicates equal contribution Preprint. Under review.

DeepFreight: A Model-free Deep-reinforcement-learning-based Algorithm for Multi-transfer Freight Delivery

“…As a related area, researches about the ride-sharing system are introduced in this part. To handle the dynamic requests in this scenario, reinforcement learning aided approaches for efficient vehicle-dispatch and passenger-matching have been proposed in [12], [13], [14]. However, these approaches don't consider passengers going over multiple hops (transfers).…”

DeepFreight: A Model-free Deep-reinforcement-learning-based Algorithm for Multi-transfer Freight Delivery

“…Multi-hop Ride-Sharing: To handle the dynamic requests in ride-sharing systems, reinforcement learning aided approaches for efficient vehicle-dispatch and passengermatching have been proposed in (Oda and Joe-Wong 2018;Al-Abbasi, Ghosh, and Aggarwal 2019;de Lima et al 2020;. However, these approaches don't consider passengers going over multiple hops, which has the potential to greatly increase the ride availability and reduce emissions (Teubner and Flath 2015).…”