Data-Driven Simulation of Ride-Hailing Services using Imitation and Reinforcement Learning

TL;DR

This paper introduces a data-driven simulation framework combining imitation and reinforcement learning to model driver behavior in ride-hailing services, enabling safe experimentation with platform parameters.

Contribution

It presents a novel hybrid approach that uses behavioral cloning and reinforcement learning to simulate and adapt driver behaviors in a dynamic environment.

Findings

Successfully mimics driver behavior using real-world data

Allows platforms to predict driver reactions to parameter changes

Provides a safe, cost-effective testing environment

Abstract

The rapid growth of ride-hailing platforms has created a highly competitive market where businesses struggle to make profits, demanding the need for better operational strategies. However, real-world experiments are risky and expensive for these platforms as they deal with millions of users daily. Thus, a need arises for a simulated environment where they can predict users' reactions to changes in the platform-specific parameters such as trip fares and incentives. Building such a simulation is challenging, as these platforms exist within dynamic environments where thousands of users regularly interact with one another. This paper presents a framework to mimic and predict user, specifically driver, behaviors in ride-hailing services. We use a data-driven hybrid reinforcement learning and imitation learning approach for this. First, the agent utilizes behavioral cloning to mimic driver behavior using a real-world data set. Next, reinforcement learning is applied on top of the pre-trained agents in a simulated environment, to allow them to adapt to changes in the platform. Our framework provides an ideal playground for ride-hailing platforms to experiment with platform-specific parameters to predict drivers' behavioral patterns.